© 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. 127818
    Prev
    Next
    INDEX
    Explanations

    general + types

    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
     merciless
    -1.88
     présentent
    -1.71
     produisent
    -1.70
     tiga
    -1.66
    UTA
    -1.63
    隳
    -1.63
     étaient
    -1.63
    )
    -1.61
    の違い
    -1.60
    РЫ
    -1.57
    POSITIVE LOGITS
    7
    3.08
    1
    2.80
    6
    2.75
    8
    2.75
    5
    2.53
    3
    2.39
    2
    2.38
    4
    2.36
    9
    2.22
    0
    2.17
    Activations Density 0.053%

    No Known Activations