© 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. 22343
    Prev
    Next
    INDEX
    Explanations

    acquisition target, litigation target, transcription target

    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
    Ḳ
    -1.34
    addChild
    -1.33
    still
    -1.27
    いしい
    -1.24
    гий
    -1.24
     stille
    -1.23
     flotte
    -1.22
     vont
    -1.21
    Still
    -1.21
    tled
    -1.21
    POSITIVE LOGITS
     by
    2.47
     more
    1.97
     or
    1.86
     of
    1.76
     most
    1.72
     every
    1.69
     with
    1.64
     in
    1.61
     Because
    1.57
     until
    1.55
    Activations Density 0.076%

    No Known Activations