© 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. 8408
    Prev
    Next
    INDEX
    Explanations

    questions beginning with why

    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
     a
    -1.97
     pizarra
    -1.61
    ]
    -1.60
    ﹍﹍
    -1.59
     eigentliche
    -1.56
     sichere
    -1.49
    穑
    -1.45
     interesados
    -1.40
    -1.40
    sleeve
    -1.39
    POSITIVE LOGITS
    7
    1.76
    where
    1.52
    Surprisingly
    1.50
    發現
    1.44
    Recently
    1.41
    from
    1.41
    Примеча
    1.39
    2
    1.39
    Where
    1.38
    他已经
    1.38
    Activations Density 0.018%

    No Known Activations