© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65637
    Prev
    Next
    INDEX
    Explanations

    section headers and specific entities

    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_34/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
     so
    -1.68
     one
    -1.27
     or
    -1.23
     at
    -1.20
     informar
    -1.18
     utterly
    -1.18
     cleverly
    -1.17
     every
    -1.16
     some
    -1.15
     all
    -1.14
    POSITIVE LOGITS
     colossal
    1.29
    鴴
    1.20
     firs
    1.20
     Allows
    1.16
    mainly
    1.16
    discussed
    1.15
     ridiculously
    1.15
     mediocre
    1.13
     streamlining
    1.13
     ſch
    1.12
    Activations Density 0.000%

    No Known Activations