© 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. 96460
    Prev
    Next
    INDEX
    Explanations

    will find

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

    explanation about understanding

    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
    er
    0.47
    
    0.46
     dBASE
    0.46
    eper
    0.46
    ені
    0.45
    expiration
    0.45
    Air
    0.45
    িয়া
    0.45
    tie
    0.44
    i
    0.44
    POSITIVE LOGITS
     hedon
    0.50
     السم
    0.45
     تعلم
    0.44
     dosta
    0.44
    getNome
    0.43
     اللغة
    0.42
     страну
    0.42
     modernity
    0.41
     تجي
    0.40
     surname
    0.40
    Activations Density 0.000%

    No Known Activations