© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57411
    Prev
    Next
    INDEX
    Explanations

    sizeable community

    np_acts-logits-general · gemini-2.5-flash-lite

    code formatting and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Here
    0.58
    १
    0.50
     கலா
    0.50
    начала
    0.48
    Mình
    0.48
    REVIEW
    0.48
     चलो
    0.48
    Politics
    0.47
    राष्ट
    0.46
    व
    0.46
    POSITIVE LOGITS
     advantages
    0.52
     redox
    0.52
     alkene
    0.52
     pH
    0.49
     salinity
    0.48
     subgraph
    0.48
     readline
    0.48
     hydrating
    0.48
     substrate
    0.48
     regex
    0.47
    Activations Density 0.000%

    No Known Activations