© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39162
    Prev
    Next
    INDEX
    Explanations

    data structures and collections

    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_22/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
     and
    -1.09
     with
    -1.03
     on
    -0.96
    lindung
    -0.93
    Inters
    -0.88
    煌
    -0.88
    classNames
    -0.88
    FEB
    -0.86
    backen
    -0.86
     branding
    -0.81
    POSITIVE LOGITS
     będ
    1.20
    Schicken
    1.13
     consisting
    1.13
     구성
    1.09
     CHECKBOX
    1.08
     containing
    1.05
     목록
    1.04
    Aufbau
    1.04
    他们是
    1.02
     multicolore
    1.01
    Activations Density 0.040%

    No Known Activations