© 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. 123551
    Prev
    Next
    INDEX
    Explanations

    helplessness and vulnerability

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

    helplessness and foreign you/many

    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
    Not in Any Lists

    No Comments

    Negative Logits
    odikwa
    0.51
    hydrocèle
    0.51
    而在
    0.48
     baseX
    0.45
     biosynthesis
    0.44
     Είναι
    0.44
    龺
    0.43
     propagation
    0.43
    риш
    0.43
    াদক
    0.43
    POSITIVE LOGITS
     birçok
    0.53
     helplessly
    0.51
    0.47
     찾아
    0.45
    आप
    0.44
     आप
    0.44
     অনেকেই
    0.43
    กับ
    0.43
    elbe
    0.42
    หลาย
    0.41
    Activations Density 0.004%

    No Known Activations