© 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. 236033
    Prev
    Next
    INDEX
    Explanations

    is followed by a word

    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
    MULT
    0.54
    jx
    0.49
    DN
    0.49
    😮
    0.46
    animate
    0.46
    sdx
    0.46
    DAN
    0.46
    RICAL
    0.46
    INGTON
    0.45
    CONF
    0.45
    POSITIVE LOGITS
     Activities
    0.52
     Playa
    0.48
     cosidd
    0.48
     pli
    0.47
     projeto
    0.47
     contiene
    0.46
    摒
    0.46
    ’;
    0.45
     coscienza
    0.45
     thru
    0.45
    Activations Density 0.000%

    No Known Activations