© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 140076
    Prev
    Next
    INDEX
    Explanations

    DFS, death, spread, tell

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

    scalar quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ißler
    0.50
    ఒ
    0.50
    顼
    0.50
    Воз
    0.48
    ків
    0.47
    ählt
    0.47
    ztat
    0.47
    Missense
    0.46
    DataMat
    0.46
    ле
    0.46
    POSITIVE LOGITS
    .
    0.51
     congreg
    0.48
     economics
    0.48
     salles
    0.47
     sostenibilidad
    0.46
     congregation
    0.46
     दि
    0.44
     brazilian
    0.44
     wage
    0.44
     εκ
    0.43
    Activations Density 0.000%

    No Known Activations