© 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. 34-GEMMASCOPE-RES-131K
    4. 108277
    Prev
    Next
    INDEX
    Explanations

    review from faculty

    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_34/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
    <strong>
    -1.11
     Belén
    -1.02
     عوض
    -1.02
    🤚
    -1.02
    ంలో
    -1.01
    €,
    -0.99
    🕉
    -0.99
    USTIN
    -0.98
    <b>
    -0.97
     Prova
    -0.97
    POSITIVE LOGITS
    </strong>
    2.67
    </h2>
    2.66
    </b>
    2.53
    </em>
    2.31
    </i>
    2.14
    }
    1.91
    </
    1.80
    .}
    1.59
    :}
    1.57
    </h3>
    1.52
    Activations Density 0.011%

    No Known Activations