© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40285
    Prev
    Next
    INDEX
    Explanations

    measuring and calculating quantified data

    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
    }
    -3.03
    ፳
    -2.38
    菔
    -2.31
    只剩下
    -2.25
    孖
    -2.23
    一切都
    -2.17
     LIKE
    -2.16
     ausdrücklich
    -2.14
    <>();
    -2.14
    achios
    -2.13
    POSITIVE LOGITS
    哢
    2.45
     quieres
    2.45
    It
    2.42
    re
    2.42
    ↵
    2.14
    o
    2.13
     delicioso
    2.13
     afast
    2.09
    on
    2.08
    ings
    2.08
    Activations Density 0.041%

    No Known Activations