© 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. 40667
    Prev
    Next
    INDEX
    Explanations

    before you decide

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

    mistake, excessive, reaction, fiction

    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
     Sereth
    0.45
    ຜະລ
    0.44
     সত্ত্বেও
    0.43
    ogenen
    0.43
    锉
    0.42
     Mildred
    0.42
    वारे
    0.42
    াঙ্গা
    0.41
    皆さん
    0.41
    antiene
    0.41
    POSITIVE LOGITS
     cáps
    0.42
    弱
    0.41
     groove
    0.41
     mama
    0.40
     outage
    0.40
    )$.
    0.40
     ഗോ
    0.40
     saudável
    0.39
     league
    0.39
     hoo
    0.38
    Activations Density 0.000%

    No Known Activations