© 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. 94651
    Prev
    Next
    INDEX
    Explanations

    only valid

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

    chicken and eggs

    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
    奧
    0.49
    لر
    0.47
    升
    0.44
     直
    0.43
    Asc
    0.43
    奥
    0.43
    coal
    0.43
    エキス
    0.43
    竴
    0.43
    はもちろん
    0.43
    POSITIVE LOGITS
     Yog
    0.54
     mercenary
    0.52
     grieving
    0.50
     mafia
    0.47
     devoured
    0.47
     summar
    0.47
     monumental
    0.47
    ખો
    0.46
     melamine
    0.46
     endeavoured
    0.46
    Activations Density 0.000%

    No Known Activations