© 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. 22-GEMMASCOPE-RES-131K
    7. 65810
    Prev
    Next
    INDEX
    Explanations

    numbers, citations, or technical terms

    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
     parís
    -1.22
     barbati
    -1.19
     olacaktır
    -1.17
    wiſe
    -1.14
    หรือ
    -1.14
     знал
    -1.13
    målet
    -1.11
    ⓡ
    -1.11
    zné
    -1.10
     bershka
    -1.09
    POSITIVE LOGITS
     at
    1.29
     further
    1.19
     second
    1.16
     even
    1.15
     another
    1.10
     just
    1.08
     one
    1.07
     with
    1.05
     další
    1.05
     No
    1.04
    Activations Density 0.044%

    No Known Activations