© 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. 68259
    Prev
    Next
    INDEX
    Explanations

    temporary states or actions

    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
    ⟐
    -2.23
    翆
    -2.19
     BOTH
    -2.19
    OUTUBE
    -2.11
    咄
    -2.08
    mberto
    -2.06
     reempla
    -2.03
     Both
    -2.03
    糠
    -2.03
    괭
    -2.02
    POSITIVE LOGITS
    '
    3.00
    ?”
    2.69
     was
    2.59
    ₶
    2.52
    ed
    2.52
     歳
    2.28
     fährt
    2.28
    1
    2.27
     juſt
    2.22
    剛剛
    2.20
    Activations Density 0.004%

    No Known Activations