© 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. 34-GEMMASCOPE-RES-131K
    7. 78569
    Prev
    Next
    INDEX
    Explanations

    sum of frequency, digits, or rules

    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
    縞
    -0.89
    に伴
    -0.84
    %:
    -0.82
     yaşad
    -0.82
     patří
    -0.79
    controllers
    -0.77
    Bmp
    -0.77
     size
    -0.77
     Werken
    -0.77
     пришли
    -0.76
    POSITIVE LOGITS
    sum
    1.43
    Sum
    1.21
    matory
    1.20
    mmation
    1.19
    mation
    1.13
     Sum
    1.10
    mands
    1.08
    atorio
    1.04
    mability
    0.96
     SUM
    0.94
    Activations Density 0.012%

    No Known Activations