© 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. 37094
    Prev
    Next
    INDEX
    Explanations

    articles related to specific topics

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

    formats, lists, and specific items

    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
     VND
    0.51
    )
    0.47
     GSK
    0.45
     fasci
    0.44
     Kanton
    0.43
     HSBC
    0.42
    UMN
    0.42
     perishable
    0.42
     VERY
    0.41
    removeFrom
    0.41
    POSITIVE LOGITS
    堞
    0.50
    èbres
    0.49
     genießen
    0.48
     চলবে
    0.48
    支撑
    0.46
     платье
    0.46
    ാനും
    0.46
     त्यावर
    0.45
    કિસ્
    0.45
     grooves
    0.44
    Activations Density 0.000%

    No Known Activations