© 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. 7780
    Prev
    Next
    INDEX
    Explanations

    Samsung rolls out

    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
     on
    -1.80
    鸶
    -1.74
     already
    -1.46
     doméstico
    -1.44
    文學
    -1.44
    ون
    -1.41
    :,,
    -1.40
    就连
    -1.38
     firft
    -1.37
     need
    -1.34
    POSITIVE LOGITS
    atother
    1.43
     dents
    1.37
     and
    1.34
    苙
    1.34
     prosegu
    1.31
    ensore
    1.31
    ꈊ
    1.30
    дых
    1.28
    дәбият
    1.28
     लड़
    1.27
    Activations Density 0.000%

    No Known Activations