© 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. 191728
    Prev
    Next
    INDEX
    Explanations

    names or numbers followed by action

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

    acknowledging specific actions or states

    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
    THIS
    0.49
    ELECTRON
    0.48
    LinkForm
    0.47
     dieser
    0.47
     ataupun
    0.46
    قتي
    0.46
    
    0.45
    IH
    0.45
    IIT
    0.45
    पहरण
    0.45
    POSITIVE LOGITS
     angry
    0.46
     зву
    0.46
    ској
    0.45
    颊
    0.43
     Gérard
    0.43
     голос
    0.42
     प्रश्न
    0.42
     आवाज
    0.42
     bumpy
    0.42
     grainy
    0.42
    Activations Density 0.000%

    No Known Activations