© 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. 34-GEMMASCOPE-RES-131K
    7. 119014
    Prev
    Next
    INDEX
    Explanations

    code elements and common identifiers

    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
     WebDriverWait
    -1.29
    rogens
    -1.25
    nae
    -1.24
     vermel
    -1.21
     skola
    -1.20
    ',
    -1.19
     высоты
    -1.19
    aaaa
    -1.16
    thday
    -1.14
     internetu
    -1.13
    POSITIVE LOGITS
    始まり
    1.05
     undoubtedly
    0.95
    パートナー
    0.89
     tailored
    0.88
     cumbersome
    0.85
    始まる
    0.85
    便利な
    0.85
     tenacious
    0.84
     assig
    0.84
     seems
    0.84
    Activations Density 0.038%

    No Known Activations