© 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. 12241
    Prev
    Next
    INDEX
    Explanations

    file headers and code snippets

    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
     Because
    -1.26
     Since
    -1.25
     vermeld
    -1.15
    なんだろう
    -1.09
     With
    -1.09
     When
    -1.09
     what
    -1.09
     also
    -1.09
     not
    -1.07
     appears
    -1.07
    POSITIVE LOGITS
     grote
    1.16
     leſs
    1.13
     ホルダー
    1.12
     disgruntled
    1.10
     projeto
    1.10
    ndef
    1.09
     fala
    1.09
    苤
    1.08
    ౩
    1.05
     ceux
    1.04
    Activations Density 0.002%

    No Known Activations