© 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. 127696
    Prev
    Next
    INDEX
    Explanations

    immediate danger

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

    technical explanations and code

    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
    f
    0.53
    ുമോ
    0.49
    عرض
    0.49
    t
    0.47
    textSize
    0.44
    ീ
    0.44
    z
    0.44
    ach
    0.43
    r
    0.43
    i
    0.43
    POSITIVE LOGITS
     Lah
    0.53
    垣
    0.50
    人文
    0.47
     Hafen
    0.47
    统
    0.46
     Kyrgyzstan
    0.45
     Tajikistan
    0.44
     garrison
    0.44
     Gah
    0.44
    󰀄
    0.44
    Activations Density 0.000%

    No Known Activations