© 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. 166262
    Prev
    Next
    INDEX
    Explanations

    brand tracking or content planning

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

    access information and tools

    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
    removeClass
    0.56
    nikom
    0.50
    뗄
    0.50
    REFLECTION
    0.49
    띈
    0.49
     groaned
    0.49
     rameaux
    0.48
    득
    0.48
    ಾವ್
    0.48
    рение
    0.47
    POSITIVE LOGITS
     uk
    0.51
     Se
    0.50
     এব
    0.49
    et
    0.48
    ed
    0.47
     Um
    0.46
     Uk
    0.45
     Sch
    0.45
     e
    0.44
    aat
    0.44
    Activations Density 0.000%

    No Known Activations