© 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. 16016
    Prev
    Next
    INDEX
    Explanations

    argued

    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
     only
    -1.30
     after
    -1.27
     which
    -1.27
    larla
    -1.23
     if
    -1.20
    자인
    -1.13
     finas
    -1.11
    捺
    -1.10
     some
    -1.10
     vertes
    -1.09
    POSITIVE LOGITS
    ∂
    1.27
     abandonné
    1.20
     voient
    1.20
    CppMethod
    1.19
    inset
    1.19
     you
    1.19
     inferiore
    1.18
    ܇
    1.18
    不高
    1.18
    烀
    1.16
    Activations Density 0.000%

    No Known Activations