© 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. 44306
    Prev
    Next
    INDEX
    Explanations

    citations with years

    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
    ]--;
    -1.65
    )',
    -1.63
    \},
    -1.58
    </th>
    -1.56
    \}$,
    -1.56
    taler
    -1.55
    "},
    -1.55
    }',
    -1.55
    )",
    -1.52
    '];
    
    -1.47
    POSITIVE LOGITS
    0
    1.97
    1
    1.41
     czasem
    1.39
     distintos
    1.34
     necesitar
    1.29
    从来
    1.25
     разные
    1.23
     been
    1.21
     bekannte
    1.21
    ad
    1.20
    Activations Density 0.014%

    No Known Activations