© 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. 69205
    Prev
    Next
    INDEX
    Explanations

    jailed suspect

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

    gang violence, police, attack

    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
     নগদ
    0.47
     पेंसिल
    0.43
    Agent
    0.43
     Peyton
    0.43
     Oatmeal
    0.43
     কবল
    0.43
     ቫ
    0.42
     आरोप
    0.41
    被告
    0.41
    賬
    0.41
    POSITIVE LOGITS
     focussed
    0.41
    ''.
    0.40
    packages
    0.40
    我们会
    0.39
    append
    0.39
    ופי
    0.39
    settings
    0.38
     necessariamente
    0.38
    '".
    0.38
    package
    0.38
    Activations Density 0.036%

    No Known Activations