© 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. 71345
    Prev
    Next
    INDEX
    Explanations

    output text only

    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
     Beziehung
    0.41
    imidazol
    0.41
     impresa
    0.39
    
    0.39
     exponential
    0.38
     Relationship
    0.37
    އ
    0.37
    ständ
    0.37
     रोगियों
    0.36
    ield
    0.36
    POSITIVE LOGITS
    onRouteChange
    0.44
    EditText
    0.44
     robes
    0.41
     Massacre
    0.41
     Adapun
    0.40
    ヤモンド
    0.40
    Hval
    0.40
    🤲
    0.39
     платы
    0.39
     тексти
    0.39
    Activations Density 0.008%

    No Known Activations