© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 129580
    Prev
    Next
    INDEX
    Explanations

    OBITUARY or file format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.57
    ⁈
    -1.51
     by
    -1.48
    嗚
    -1.48
     during
    -1.47
     with
    -1.45
     when
    -1.45
    Läh
    -1.39
    しますが
    -1.38
     escondido
    -1.38
    POSITIVE LOGITS
    _
    1.97
    ’
    1.81
    1.81
    </b>
    1.76
    <i>
    1.63
    </h1>
    1.63
    –
    1.59
    </i>
    1.58
    </strong>
    1.55
     attentes
    1.54
    Activations Density 0.003%

    No Known Activations