© 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. 26065
    Prev
    Next
    INDEX
    Explanations

    pattern before specific words

    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
    ,
    0.47
    ↵
    0.43
    …
    0.40
    ।
    0.38
    ;
    0.36
     in
    0.36
    .
    0.33
     во
    0.33
    】
    0.33
    !
    0.32
    POSITIVE LOGITS
     pandémie
    0.42
    ร้อม
    0.41
    膯
    0.40
     densité
    0.40
    ्युअर
    0.40
     varietà
    0.39
    вершена
    0.39
     applicazioni
    0.39
    OnFileChange
    0.39
     cerveau
    0.38
    Activations Density 0.000%

    No Known Activations