© 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. 10-GEMMASCOPE-RES-131K
    7. 67710
    Prev
    Next
    INDEX
    Explanations

    myths and misconceptions

    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_10/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
    ?"
    -1.75
     a
    -1.71
     ४
    -1.47
    剮
    -1.46
    panzer
    -1.46
    innerWidth
    -1.45
     srdce
    -1.41
    präsident
    -1.38
    珖
    -1.36
     â
    -1.35
    POSITIVE LOGITS
     about
    1.99
     there
    1.87
    mathrm
    1.67
    还要
    1.55
    
    1.48
    selbe
    1.46
    but
    1.45
    也有
    1.44
    栃
    1.43
     będziesz
    1.41
    Activations Density 0.040%

    No Known Activations