© 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. 65761
    Prev
    Next
    INDEX
    Explanations

    new

    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
     their
    -1.28
     by
    -1.22
     anything
    -1.20
     all
    -1.16
     its
    -1.13
     each
    -1.07
     itself
    -1.07
     to
    -1.07
     registrazione
    -1.01
    が
    -1.01
    POSITIVE LOGITS
    óval
    1.12
    如图
    1.11
     jambes
    1.10
     étrang
    1.09
     décé
    1.09
     sincero
    1.09
    を探す
    1.05
     peluche
    1.02
     riscos
    1.01
    ケモン
    0.98
    Activations Density 0.014%

    No Known Activations