© 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. 97920
    Prev
    Next
    INDEX
    Explanations

    consideration, clients, results

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

    original responses, data required

    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
    ;
    0.55
    <0x80>
    0.52
    0.52
     กำ
    0.49
    ,!
    0.47
    ,(
    0.47
     எனவும்
    0.46
    !
    0.46
     memperkenalkan
    0.46
    ,[
    0.44
    POSITIVE LOGITS
    ركه
    0.53
     amyl
    0.52
     plasmids
    0.49
     pulses
    0.49
     slugs
    0.48
    ريض
    0.48
    emails
    0.47
     dovol
    0.46
     minimizes
    0.46
     puffs
    0.46
    Activations Density 0.000%

    No Known Activations