© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3138
    Prev
    Next
    INDEX
    Explanations

    refusal of harmful content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     easel
    1.25
     cinematography
    1.18
     baton
    1.17
     graffiti
    1.16
     work
    1.15
    مسه
    1.08
    鈑
    1.07
    GAAP
    1.07
     punch
    1.07
     comics
    1.06
    POSITIVE LOGITS
    琅
    1.32
    Wald
    1.31
    omer
    1.30
    ̣ng
    1.22
    GroupName
    1.22
    inek
    1.21
    ORDERS
    1.21
    әр
    1.20
    fir
    1.19
    ucht
    1.18
    Activations Density 0.028%

    No Known Activations