© 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. 126701
    Prev
    Next
    INDEX
    Explanations

    seconds folks

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

    difficult to filter or reject

    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
     proposed
    0.51
    开放
    0.49
    ä
    0.49
    void
    0.48
    Employment
    0.48
     प्रस्ताव
    0.47
    Proposal
    0.47
     <
    0.46
    The
    0.46
    การ
    0.46
    POSITIVE LOGITS
     seasonings
    0.62
     hamburgers
    0.57
     mascara
    0.56
     policías
    0.56
     pecados
    0.55
     filtros
    0.54
    পুরের
    0.54
     burgers
    0.53
     americanos
    0.53
    ᒎ
    0.53
    Activations Density 0.002%

    No Known Activations