© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8664
    Prev
    Next
    INDEX
    Explanations

    ranking and ordering

    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
    '))
    1.66
    '),
    1.56
     %),
    1.56
    `),
    1.52
    </h5>
    1.50
    ’),
    1.50
    ')),
    1.41
    ']),
    1.36
    %),
    1.36
    )),
    1.35
    POSITIVE LOGITS
    '";
    1.98
    ]";
    1.86
    }";
    1.86
    /";
    1.85
     ";//
    1.76
    ";//
    1.75
    .";
    1.74
    ...";
    1.71
    !";
    1.71
    :";
    1.70
    Activations Density 0.039%

    No Known Activations