© 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. 71450
    Prev
    Next
    INDEX
    Explanations

    planning ahead

    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
    }
    -3.61
     o
    -2.56
    ↵↵
    -2.52
    -
    -2.44
    be
    -2.41
    みたら
    -2.39
     ‘
    -2.34
     exquisite
    -2.33
     p
    -2.33
     t
    -2.33
    POSITIVE LOGITS
     frança
    3.16
     inoxydable
    3.03
     pauv
    2.86
    ientras
    2.80
     aussit
    2.78
    很喜欢
    2.72
    苼
    2.67
     anún
    2.63
    媜
    2.61
    CHREIBUNG
    2.59
    Activations Density 0.004%

    No Known Activations