© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 47766
    Prev
    Next
    INDEX
    Explanations

    animations and transitions

    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
    moji
    -0.74
    LYN
    -0.70
     almeno
    -0.70
    Equation
    -0.69
    但
    -0.69
    рослав
    -0.69
     BATT
    -0.68
    arat
    -0.68
    говой
    -0.67
     SPOILERS
    -0.66
    POSITIVE LOGITS
     slide
    1.15
    slide
    1.06
     ${({
    0.98
     Slide
    0.98
     enter
    0.93
     Exit
    0.93
    zzling
    0.85
    Slide
    0.85
     Enter
    0.83
     exit
    0.83
    Activations Density 0.002%

    No Known Activations