© 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. 22440
    Prev
    Next
    INDEX
    Explanations

    setting up

    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
    2
    -3.63
    3
    -3.08
    ↵
    -2.89
    8
    -2.78
    5
    -2.78
    0
    -2.59
    7
    -2.53
    6
    -2.52
    4
    -2.45
    彞
    -2.38
    POSITIVE LOGITS
     a
    2.42
     However
    2.20
    こういった
    2.19
     alebo
    2.19
     razões
    2.13
    ioneta
    2.11
    ꙳
    2.11
    澇
    2.09
     edgy
    2.09
    .”
    2.09
    Activations Density 0.020%

    No Known Activations