© 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. 34-GEMMASCOPE-RES-131K
    7. 107222
    Prev
    Next
    INDEX
    Explanations

    comparison operators

    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_34/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
     even
    -1.24
     by
    -1.20
    Data
    -1.19
     although
    -1.18
    が
    -1.17
     from
    -1.16
    日を
    -1.15
    Get
    -1.13
     mostly
    -1.10
     ngunit
    -1.08
    POSITIVE LOGITS
     見える
    1.35
    colgante
    1.33
    様な
    1.32
    為に
    1.30
    ようになる
    1.25
    シャレ
    1.25
    場所で
    1.17
     immense
    1.16
    遠い
    1.12
     ort
    1.11
    Activations Density 0.031%

    No Known Activations