© 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. 22-GEMMASCOPE-RES-131K
    7. 129526
    Prev
    Next
    INDEX
    Explanations

    when dealing or preparing

    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
     berupa
    -1.04
     only
    -0.99
     can
    -0.94
     by
    -0.94
     finden
    -0.93
     тонн
    -0.91
     допусти
    -0.91
     sehen
    -0.90
     don
    -0.90
     kebaikan
    -0.90
    POSITIVE LOGITS
     answers
    1.00
    𝔗
    1.00
    groupId
    0.99
    ḿ
    0.98
     traged
    0.91
     approach
    0.91
     answer
    0.90
     MINOR
    0.89
    handling
    0.89
     jā
    0.88
    Activations Density 0.047%

    No Known Activations