© 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. 79095
    Prev
    Next
    INDEX
    Explanations

    html attributes and states

    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
     PAM
    -0.84
    >{{
    -0.81
    icylic
    -0.79
     Ordering
    -0.77
    ymm
    -0.77
    errHandler
    -0.75
    ORET
    -0.75
     अं
    -0.75
    ambient
    -0.74
     iunie
    -0.73
    POSITIVE LOGITS
     checked
    1.22
    SELECTED
    1.13
     style
    1.11
    checked
    1.08
     selected
    1.03
     class
    0.99
    selected
    0.98
     disabled
    0.93
     stile
    0.93
    Checked
    0.92
    Activations Density 0.024%

    No Known Activations