© 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. 208209
    Prev
    Next
    INDEX
    Explanations

    scientists are

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

    protection and opposition measures

    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
    }}}\
    0.47
    前辈
    0.45
     unrel
    0.44
     seasonality
    0.43
    Currently
    0.43
     右利き
    0.43
    iply
    0.42
     переме
    0.42
     usu
    0.41
     অবস্থানে
    0.41
    POSITIVE LOGITS
    ?";
    0.45
     Bảo
    0.44
    ?;
    0.44
    ؟.
    0.43
    ափ
    0.42
    nofollow
    0.42
    nous
    0.41
    форд
    0.41
    ?',
    0.41
    ขอ
    0.41
    Activations Density 0.000%

    No Known Activations