© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12020
    Prev
    Next
    INDEX
    Explanations

    refusal due to harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    אים
    2.29
    
    2.17
    toHave
    2.06
     Powerful
    2.00
    يه
    1.99
    ीत
    1.96
     toString
    1.95
     Current
    1.94
    ן
    1.93
    grat
    1.93
    POSITIVE LOGITS
    ół
    2.02
    acen
    1.82
    ClkInitStruct
    1.80
     <$>
    1.78
    ోతి
    1.78
    র্তি
    1.77
     الشيطان
    1.76
    geoType
    1.76
    ércoles
    1.76
    łac
    1.75
    Activations Density 0.052%

    No Known Activations