© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4162
    Prev
    Next
    INDEX
    Explanations

    installing python packages with pip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reflected
    0.77
    shint
    0.74
    рактери
    0.73
     일으
    0.73
     Nossa
    0.71
     concomitant
    0.70
     ء
    0.70
     interfering
    0.70
    ोजन
    0.69
    獬
    0.69
    POSITIVE LOGITS
    //
    0.74
     Export
    0.70
     outside
    0.69
     Terrace
    0.67
     export
    0.67
     వర్
    0.64
     Latvian
    0.63
    Pension
    0.62
    ||
    0.62
    Hungary
    0.61
    Activations Density 0.028%

    No Known Activations