© 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. 22-GEMMASCOPE-RES-131K
    7. 33019
    Prev
    Next
    INDEX
    Explanations

    guide or tips

    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_22/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
     only
    -1.31
     without
    -1.16
    cribed
    -1.15
    taya
    -1.11
    rrrrrr
    -1.08
    ercise
    -1.07
    fanart
    -1.06
     at
    -1.05
    ريكي
    -1.05
    rrrrrrrr
    -1.05
    POSITIVE LOGITS
     advice
    2.11
     help
    1.93
     you
    1.88
     helpful
    1.76
     guide
    1.74
     advises
    1.64
     tips
    1.60
     answers
    1.59
     useful
    1.53
    ช่วย
    1.43
    Activations Density 0.082%

    No Known Activations