© 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. 203779
    Prev
    Next
    INDEX
    Explanations

    limited, filed, services, studying, outstanding

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

    refuse to answer inappropriate requests

    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
     لم
    0.45
    勍
    0.43
     তারিখ
    0.42
    श्ती
    0.42
    летие
    0.42
    ahlia
    0.42
    ارہ
    0.42
    竰
    0.41
    holo
    0.41
    กับ
    0.41
    POSITIVE LOGITS
     deceiving
    0.54
     avenge
    0.54
     vaz
    0.49
    porcion
    0.48
    返す
    0.48
     francesa
    0.46
     henceforth
    0.46
    氨
    0.46
    riterion
    0.45
    rosion
    0.45
    Activations Density 0.001%

    No Known Activations