© 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. 223050
    Prev
    Next
    INDEX
    Explanations

    facilitate insertion

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

    examples and explanations

    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
    秫
    0.46
    দেশিক
    0.46
    Country
    0.45
    upaten
    0.45
    োজনের
    0.45
     সামান্য
    0.45
     Country
    0.44
     Science
    0.43
    చ్చ
    0.42
     ligands
    0.42
    POSITIVE LOGITS
    ک
    0.50
    衝突
    0.48
    ಊ
    0.47
    麻煩
    0.46
    エ
    0.45
    ھ
    0.44
    اح
    0.43
    use
    0.43
    الم
    0.42
    リスク
    0.42
    Activations Density 0.001%

    No Known Activations