© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91635
    Prev
    Next
    INDEX
    Explanations

    frame buffer

    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
    IFICACIÓN
    -0.76
     đậm
    -0.70
    IENT
    -0.68
     Joining
    -0.67
    êu
    -0.65
     join
    -0.64
     sleepless
    -0.64
     coolers
    -0.64
    pasien
    -0.63
    rews
    -0.63
    POSITIVE LOGITS
     buffer
    1.33
    buffer
    1.03
     buffers
    1.01
     off
    0.99
     Frame
    0.94
     Buffer
    0.93
    Buffer
    0.92
     Attachment
    0.92
     back
    0.91
    buffers
    0.91
    Activations Density 0.022%

    No Known Activations