© 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. 178046
    Prev
    Next
    INDEX
    Explanations

    always be, at a, so that, protection service

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

    measuring ability and 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
    дування
    0.54
    䡉
    0.52
     peremptory
    0.48
    ोबर
    0.47
    ವಾಗಿ
    0.46
    ודי
    0.45
    好き
    0.45
    იდან
    0.45
    𝙢
    0.45
    篒
    0.45
    POSITIVE LOGITS
    lia
    0.53
    li
    0.49
    ế
    0.49
    пь
    0.47
    ponge
    0.46
    acom
    0.45
    inv
    0.45
    nj
    0.45
     decir
    0.44
    lı
    0.44
    Activations Density 0.000%

    No Known Activations