© 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. 34-GEMMASCOPE-RES-131K
    7. 78763
    Prev
    Next
    INDEX
    Explanations

    listing criteria or options

    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
    ).
    -1.56
    》。
    -1.45
    "].
    -1.41
    }$.
    -1.39
    '].
    -1.38
    ».
    -1.38
    」。
    -1.34
    ].
    -1.30
    》.
    -1.30
    })$.
    -1.27
    POSITIVE LOGITS
    ,</
    1.56
     '.',
    1.47
     ②
    1.34
     '*',
    1.34
     secondly
    1.31
     "*",
    1.31
    ;",
    1.30
    ?,
    1.25
    ,}
    1.21
    !,
    1.17
    Activations Density 0.084%

    No Known Activations