© 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. 23445
    Prev
    Next
    INDEX
    Explanations

    business, presence, space

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

    integrating datasets

    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
    ','"
    0.47
    AMG
    0.47
    테
    0.45
    dır
    0.45
    INTERFACE
    0.45
    CONTRACT
    0.44
    ANNOT
    0.44
    GRect
    0.43
    சித்து
    0.43
     спраши
    0.43
    POSITIVE LOGITS
     unpopular
    0.45
     Invitation
    0.45
     глава
    0.44
     Infrast
    0.42
     Official
    0.41
     解
    0.41
    ริ่ม
    0.40
     但是
    0.40
     $|
    0.40
    }=-
    0.40
    Activations Density 0.000%

    No Known Activations