© 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. 38596
    Prev
    Next
    INDEX
    Explanations

    news reports and official statements

    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
     any
    -1.23
     this
    -1.13
     sogni
    -1.13
    Quanto
    -1.12
     what
    -1.12
    rą
    -1.10
    Skład
    -1.09
    Muerte
    -1.07
    Więcej
    -1.06
    Warto
    -1.06
    POSITIVE LOGITS
    </strong>
    1.71
    </h2>
    1.62
    </h1>
    1.44
    </i>
    1.41
    </b>
    1.39
     TikTok
    1.23
    </h3>
    1.22
    </em>
    1.20
    ('.');
    1.16
     '../../../../
    1.14
    Activations Density 0.048%

    No Known Activations