© 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. 22-GEMMASCOPE-RES-131K
    7. 128367
    Prev
    Next
    INDEX
    Explanations

    product and brand names

    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_22/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
    Anybody
    -1.30
    somebody
    -1.29
     acknowledgement
    -1.25
     тща
    -1.16
    volving
    -1.14
    produksi
    -1.14
     somebody
    -1.13
    ologic
    -1.12
    enoid
    -1.12
    might
    -1.11
    POSITIVE LOGITS
     with
    1.63
    🪛
    1.52
     ​​
    1.48
     of
    1.41
     in
    1.41
    ̵
    1.37
    NUMX
    1.30
    🧫
    1.25
     from
    1.23
     aktivitas
    1.20
    Activations Density 0.087%

    No Known Activations