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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10972
    Prev
    Next
    INDEX
    Explanations

    "to the" storage

    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
    .’”
    1.69
    .'”
    1.63
    ,’”
    1.60
    ).”
    1.54
    .”
    1.49
    ].”
    1.49
    ?’”
    1.45
    ).'
    1.39
    ...”
    1.37
    ,”
    1.36
    POSITIVE LOGITS
    </sup>
    2.82
    ）、
    1.95
    ）
    1.91
    ）（
    1.86
    ）,
    1.78
    ）』
    1.75
    ））
    1.67
    </h6>
    1.66
     ）
    1.64
    ），
    1.58
    Activations Density 0.009%

    No Known Activations