© 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. 39626
    Prev
    Next
    INDEX
    Explanations

    ip address or version number placeholders

    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
     to
    -2.06
     \
    -1.91
     algun
    -1.74
     какую
    -1.66
    曙
    -1.64
     گردشگری
    -1.63
     späteren
    -1.62
    虓
    -1.61
    鸸
    -1.61
     as
    -1.61
    POSITIVE LOGITS
    }
    2.64
    2
    2.45
    8
    2.42
    7
    2.41
    that
    2.33
    9
    2.30
    '
    1.98
    6
    1.91
     terutama
    1.83
     anhänger
    1.80
    Activations Density 0.066%

    No Known Activations