© 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. 199531
    Prev
    Next
    INDEX
    Explanations

    UNS R

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

    vibe check

    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
    chränk
    0.48
     기준으로
    0.46
    iją
    0.45
    Historia
    0.43
    challenges
    0.42
    촤
    0.42
    prés
    0.42
     zostały
    0.42
    Proble
    0.42
    Optimization
    0.42
    POSITIVE LOGITS
     USED
    0.49
    谍
    0.46
    乓
    0.45
    تها
    0.44
     something
    0.43
    ग्ध
    0.43
    лини
    0.43
     सप्टेंबर
    0.43
    宗
    0.43
    गरण
    0.42
    Activations Density 0.000%

    No Known Activations