© 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. 11453
    Prev
    Next
    INDEX
    Explanations

    cybersecurity operations

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

    lists sections and descriptions

    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
     \,.
    0.46
     ”.
    0.45
     ہے۔
    0.45
    ത്തിയത്
    0.45
    ”!
    0.42
     $)$.
    0.41
    ].
    0.41
     dieser
    0.41
     ہو۔
    0.40
    ™.
    0.40
    POSITIVE LOGITS
    했고
    1.05
     และ
    0.93
    었고
    0.93
    ですし
    0.93
    ”、
    0.92
     oraz
    0.80
    ）、
    0.79
    」、
    0.78
    )、
    0.73
     እንዲሁም
    0.73
    Activations Density 0.398%

    No Known Activations