© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 139158
    Prev
    Next
    INDEX
    Explanations

    less simple universally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    0.46
    layout
    0.44
    Thread
    0.43
    AS
    0.41
    कर
    0.41
     iremos
    0.41
    ThreadGroup
    0.41
    वा
    0.41
    –
    0.40
    设置
    0.40
    POSITIVE LOGITS
     വാർത്ത
    0.54
     dépass
    0.53
     littérature
    0.53
     partie
    0.49
     nuovi
    0.49
     أرض
    0.49
     RUDDER
    0.49
     Fonction
    0.48
     numéro
    0.48
     Número
    0.47
    Activations Density 0.004%

    No Known Activations