© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4072
    Prev
    Next
    INDEX
    Explanations

    refusal of inappropriate 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_12_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
    FOCUS
    1.36
     tillage
    1.26
    NEED
    1.22
    zid
    1.20
    ABAD
    1.17
    询
    1.17
    焦点
    1.17
     tasse
    1.16
    Dirt
    1.13
    agriculture
    1.12
    POSITIVE LOGITS
     vest
    1.35
     Tyne
    1.35
     ۱۹
    1.33
     Bois
    1.30
    iavelli
    1.29
     fifty
    1.28
    呤
    1.27
     Alcan
    1.27
     seventy
    1.26
    ooky
    1.25
    Activations Density 0.022%

    No Known Activations