© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7569
    Prev
    Next
    INDEX
    Explanations

    perhaps suggests alternatives

    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_22_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
     unwillingness
    0.92
    顽
    0.81
     inability
    0.81
    េស
    0.79
    疑问
    0.79
    Wr
    0.79
    slf
    0.76
     stubbornly
    0.76
     troubles
    0.76
    围
    0.75
    POSITIVE LOGITS
     puk
    0.98
     suff
    0.96
    ギ
    0.95
    يع
    0.93
     tarif
    0.90
    掐
    0.88
     setTodos
    0.87
     frosting
    0.87
     holog
    0.87
    奠
    0.87
    Activations Density 0.149%

    No Known Activations