© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57057
    Prev
    Next
    INDEX
    Explanations

    unknown or null values

    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_34/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
    ,/
    -0.88
    ,@
    -0.85
    .+
    -0.84
     %,
    -0.83
    aning
    -0.78
    '",
    -0.78
     :,
    -0.78
    のいい
    -0.77
    /+
    -0.77
    SOUND
    -0.75
    POSITIVE LOGITS
     unknown
    1.45
    ="(
    1.42
     "(
    1.38
    Unknown
    1.36
     Unknown
    1.35
     NA
    1.27
    ('--
    1.24
    UNKNOWN
    1.23
    ("(
    1.19
     неизвест
    1.19
    Activations Density 0.019%

    No Known Activations