© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22081
    Prev
    Next
    INDEX
    Explanations

    Objective-C method signatures

    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_10/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
    Surprisingly
    -1.98
    Ironically
    -1.91
    Though
    -1.91
    Also
    -1.84
    Although
    -1.82
    While
    -1.81
    Nearly
    -1.79
     было
    -1.76
    Remember
    -1.76
    Knowing
    -1.74
    POSITIVE LOGITS
     are
    2.05
    existsSync
    1.98
     is
    1.98
     OF
    1.93
    `)
    1.88
    </h5>
    1.88
     turmoil
    1.84
    嫫
    1.84
    readFileSync
    1.80
    ']
    1.79
    Activations Density 0.008%

    No Known Activations