© 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. 106991
    Prev
    Next
    INDEX
    Explanations

    dates and months

    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
     buffer
    -1.84
     Buffer
    -1.67
    Buffer
    -1.55
    buffer
    -1.48
     buf
    -1.38
     buffers
    -1.38
    BUF
    -1.26
    缓冲
    -1.22
    buf
    -1.19
    BUFFER
    -1.17
    POSITIVE LOGITS
     мэ
    0.86
     CO
    0.81
     LU
    0.81
    ్
    0.81
     Ln
    0.79
    Till
    0.75
    へと
    0.75
    ্
    0.72
     cn
    0.69
     o
    0.69
    Activations Density 0.006%

    No Known Activations