© 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. 50364
    Prev
    Next
    INDEX
    Explanations

    information for purpose

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

    written to introduce

    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
    
    0.43
    𝗷
    0.42
    для
    0.42
    ωνα
    0.42
    RAR
    0.42
    )!
    0.41
    WORKING
    0.41
     outbursts
    0.41
     FIVE
    0.41
    $$
    0.40
    POSITIVE LOGITS
     alumin
    0.50
    ل
    0.48
     Alumni
    0.46
    龛
    0.46
     প্রতিনি
    0.45
    tze
    0.45
     consentimiento
    0.44
     podataka
    0.44
     بوده
    0.44
     transact
    0.43
    Activations Density 0.000%

    No Known Activations