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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12356
    Prev
    Next
    INDEX
    Explanations

    over time

    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
     lemah
    -1.32
    Karakteristik
    -1.27
     melindungi
    -1.27
     at
    -1.26
     prévoit
    -1.21
     eût
    -1.21
    ätigung
    -1.17
    溲
    -1.17
    と思った
    -1.16
     menghindari
    -1.16
    POSITIVE LOGITS
    \
    1.48
    I
    1.41
    The
    1.41
    $
    1.41
    D
    1.41
    ،
    1.36
    J
    1.36
    f
    1.35
    L
    1.32
    It
    1.31
    Activations Density 0.019%

    No Known Activations