© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43249
    Prev
    Next
    INDEX
    Explanations

    programming code identifiers

    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
     läßt
    -1.77
     ocultar
    -1.58
     or
    -1.50
    閬
    -1.50
     other
    -1.49
     effetto
    -1.44
     onderzoek
    -1.43
    事も
    -1.43
     each
    -1.42
     idiots
    -1.42
    POSITIVE LOGITS
     \
    2.03
    :
    1.62
    _);
    1.53
    MAXN
    1.52
    __,
    1.52
    ctober
    1.50
     雰囲気
    1.40
    ])
    1.40
    xiii
    1.40
     to
    1.39
    Activations Density 0.019%

    No Known Activations