© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 188803
    Prev
    Next
    INDEX
    Explanations

    instead of

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

    anxieties about society and self

    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
    gia
    0.55
     እድ
    0.54
    魟
    0.54
     ఉపయోగ
    0.51
     அவற்ற
    0.51
     今回
    0.50
     スク
    0.50
     シェ
    0.49
    デン
    0.49
     Chesapeake
    0.49
    POSITIVE LOGITS
    Als
    0.44
    -
    0.44
    '
    0.43
     tzw
    0.42
     odpowiedzi
    0.41
     trustee
    0.40
     biał
    0.40
     flee
    0.39
    কিত
    0.39
    น์โหลด
    0.38
    Activations Density 0.001%

    No Known Activations