© 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. 65426
    Prev
    Next
    INDEX
    Explanations

    associated with or behind

    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
     sebagainya
    -1.48
    engibre
    -1.30
     podczas
    -1.22
    ٪
    -1.18
     compromising
    -1.16
     leiding
    -1.15
    çais
    -1.15
    遑
    -1.10
     litros
    -1.10
     during
    -1.10
    POSITIVE LOGITS
     it
    1.60
     this
    1.59
     these
    1.57
     each
    1.49
    Cevap
    1.28
     the
    1.26
     eier
    1.24
    denken
    1.23
     apparaissent
    1.21
     stoff
    1.16
    Activations Density 0.037%

    No Known Activations