© 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. 244686
    Prev
    Next
    INDEX
    Explanations

    register domain names

    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
     Accesat
    0.45
    мп
    0.44
    偪
    0.43
    共に
    0.43
     внимание
    0.42
    adlo
    0.41
    рифмети
    0.40
    iqueness
    0.40
    mashtami
    0.40
    डु
    0.40
    POSITIVE LOGITS
    ]}{
    0.50
     hank
    0.47
     Sonya
    0.45
     profess
    0.45
     قرب
    0.44
     تضيف
    0.44
    ’
    0.43
     änd
    0.43
     पांव
    0.42
     jost
    0.42
    Activations Density 0.000%

    No Known Activations