© 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. 12289
    Prev
    Next
    INDEX
    Explanations

    exams and tests

    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
    ‘
    -1.24
    -1.19
    de
    -1.16
    ma
    -1.14
    ba
    -1.13
    mannschaft
    -1.12
    DISABLED
    -1.10
    po
    -1.10
     into
    -1.09
    li
    -1.09
    POSITIVE LOGITS
    ּוֹ
    1.46
     rescheduled
    1.35
    皤
    1.32
    敺
    1.31
     exams
    1.30
     atriz
    1.30
     škole
    1.29
    ǔ
    1.28
     postponed
    1.27
    pixabay
    1.25
    Activations Density 0.019%

    No Known Activations