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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11338
    Prev
    Next
    INDEX
    Explanations

    film festivals and screenings

    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
     who
    -1.66
    ԝ
    -1.41
     think
    -1.31
    ߋ
    -1.27
    Who
    -1.24
    item
    -1.23
    ᧐
    -1.22
     >
    -1.19
     chanteuse
    -1.16
    geq
    -1.16
    POSITIVE LOGITS
    ﻹ
    1.45
    dokument
    1.41
    厮
    1.40
     films
    1.38
    וּ
    1.36
     film
    1.33
     február
    1.32
    "$_
    1.30
    ﻷ
    1.30
     záz
    1.28
    Activations Density 0.117%

    No Known Activations