© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 10971
    Prev
    Next
    INDEX
    Explanations

    qualifications and contrasts

    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
     and
    -1.02
     not
    -0.98
     or
    -0.97
    .")
    -0.90
     which
    -0.90
     does
    -0.85
    此外
    -0.84
    問題は
    -0.82
     without
    -0.82
    andal
    -0.82
    POSITIVE LOGITS
     but
    3.44
     nhưng
    2.45
     แต่
    2.42
     लेकिन
    2.20
     But
    2.11
     ولكن
    2.05
     mutta
    1.88
    But
    1.84
     لكن
    1.81
    but
    1.77
    Activations Density 0.097%

    No Known Activations