© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26813
    Prev
    Next
    INDEX
    Explanations

    resemblance and comparison

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

    The neuron activates on long, multisyllabic content words (e.g. long technical or descriptive nouns and verbs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    bảng
    -1.24
    tront
    -1.11
     publier
    -1.09
    ++++
    -1.05
    は約
    -1.04
     всегда
    -1.04
    僥
    -1.03
    งิน
    -1.00
    ㄌ
    -1.00
    Ꮵ
    -1.00
    POSITIVE LOGITS
     resemblance
    1.95
     reminiscent
    1.95
     similar
    1.94
     resembles
    1.91
     resembling
    1.79
     resemble
    1.77
     similarity
    1.66
     similarities
    1.66
     giống
    1.57
     parallels
    1.48
    Activations Density 0.089%

    No Known Activations