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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15419
    Prev
    Next
    INDEX
    Explanations

    code element declarations

    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
    Those
    -2.59
     their
    -2.55
    providedIn
    -2.44
    When
    -2.42
    Despite
    -2.39
    Because
    -2.38
    Perhaps
    -2.34
    After
    -2.31
    During
    -2.31
    Before
    -2.27
    POSITIVE LOGITS
    沵
    2.36
    茈
    2.28
    béco
    2.20
     ation
    2.17
    
    2.16
    ꟷ
    2.16
    
    2.13
    癭
    2.09
    
    2.05
    
    2.05
    Activations Density 0.014%

    No Known Activations