© 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. 113566
    Prev
    Next
    INDEX
    Explanations

    letter P

    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
    x
    -1.57
    or
    -1.38
    ↵↵↵
    -1.36
     was
    -1.30
     or
    -1.30
    ↵↵
    -1.30
    In
    -1.23
     zuletzt
    -1.23
    in
    -1.20
    Part
    -1.20
    POSITIVE LOGITS
     protège
    1.36
     myös
    1.31
    opheles
    1.25
    雨が
    1.21
     oiseau
    1.16
    テンション
    1.16
     Gerente
    1.16
     matières
    1.16
    lankton
    1.13
     oignon
    1.13
    Activations Density 0.178%

    No Known Activations