© 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. 103007
    Prev
    Next
    INDEX
    Explanations

    solstice equinox

    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
    勦
    -2.73
    慊
    -2.30
    褙
    -2.17
    `:
    -2.11
    知る
    -2.05
    ING
    -2.03
    玧
    -2.02
     começ
    -2.02
    筇
    -2.02
    もありますが
    -1.98
    POSITIVE LOGITS
    '
    2.67
    </sup>
    2.19
    (
    2.11
    "
    2.08
    //
    2.06
    ',
    2.03
    —
    1.98
    L
    1.97
    F
    1.97
    ]
    1.85
    Activations Density 0.008%

    No Known Activations