© 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. 115502
    Prev
    Next
    INDEX
    Explanations

    days and times

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

    avoidance of specific items or feelings

    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
    “[
    0.66
     “[
    0.59
     Whilst
    0.57
     Respondent
    0.55
    Whilst
    0.47
     Towards
    0.46
     whilst
    0.46
    "[
    0.45
     “…
    0.43
     Respondents
    0.43
    POSITIVE LOGITS
    楽しい
    0.54
    bilical
    0.52
     ಆರಂಭ
    0.51
     believer
    0.47
    raine
    0.47
     sagen
    0.46
     zegt
    0.46
     tiek
    0.45
    とか
    0.45
    メーター
    0.45
    Activations Density 0.026%

    No Known Activations