© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100374
    Prev
    Next
    INDEX
    Explanations

    ISBN and errno identifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    the text "ISBN" appearing in bibliographic or product information contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    {~
    -2.55
    ]
    -2.47
    尛
    -2.44
    </td>
    -2.42
    تیجه
    -2.36
    }
    -2.33
    corrhi
    -2.28
     When
    -2.25
     have
    -2.23
     sebagainya
    -2.22
    POSITIVE LOGITS
     aqueles
    2.72
     acostumb
    2.64
     atualmente
    2.45
    渼
    2.41
    律师
    2.38
    会在
    2.38
     sucedió
    2.33
     decenas
    2.30
     gesamte
    2.28
    骡
    2.28
    Activations Density 0.002%

    No Known Activations