© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3346
    Prev
    Next
    INDEX
    Explanations

    self-similar and similarity

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly detects terms related to self-similarity or recursive scaling (e.g. “self-similar,” “recursion,” “scaled,” “shrinkable”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nutt
    -0.77
    ኢ
    -0.69
    Tours
    -0.69
     bürger
    -0.66
     chặt
    -0.65
     Shaft
    -0.65
    splitting
    -0.65
     carcinogenic
    -0.65
    ﺧ
    -0.64
    سته
    -0.64
    POSITIVE LOGITS
     similarity
    3.39
     Similarity
    2.81
    Similarity
    2.73
    相似
    2.67
    similarity
    2.64
     SIMILAR
    2.42
     simil
    2.19
    similar
    2.16
     similarities
    2.00
     similar
    1.99
    Activations Density 0.035%

    No Known Activations