© 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. 33659
    Prev
    Next
    INDEX
    Explanations

    oily skin, long descriptions

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

    inner self, emotions, and sign

    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
    티
    0.49
    앜
    0.49
    蝿
    0.47
    膝
    0.46
    럇
    0.46
    탯
    0.45
    בום
    0.45
    ⓓ
    0.43
    ọi
    0.43
    ovej
    0.43
    POSITIVE LOGITS
     Ko
    0.56
     Sü
    0.53
     Sur
    0.53
     weitere
    0.50
     Dou
    0.49
     İ
    0.49
    psy
    0.49
     Harm
    0.48
     zu
    0.47
     Mü
    0.46
    Activations Density 0.000%

    No Known Activations