© 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. 196827
    Prev
    Next
    INDEX
    Explanations

    word classes and concepts

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

    psychological harm, anxiety, claims

    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
    on
    0.56
    6
    0.53
     FALSE
    0.52
    at
    0.52
    in
    0.51
     Brow
    0.49
    );
    0.48
    ar
    0.48
     Van
    0.48
     Bal
    0.48
    POSITIVE LOGITS
    ленной
    0.61
     âge
    0.52
     antigüedad
    0.52
     toit
    0.50
     allemand
    0.49
     takip
    0.49
     alimento
    0.48
     дней
    0.47
     infinito
    0.47
     simb
    0.47
    Activations Density 0.001%

    No Known Activations