© 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. 143815
    Prev
    Next
    INDEX
    Explanations

    corporation, BC, website, scorpions

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

    answering questions using specified data

    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
    <0xAE>
    0.44
    opre
    0.44
    ':[
    0.42
    richt
    0.41
    প্রথম
    0.41
     최고의
    0.40
    pathy
    0.40
    ():
    0.40
    hel
    0.39
     Infection
    0.39
    POSITIVE LOGITS
    ール
    0.49
    ة
    0.48
    田
    0.47
     لوڈ
    0.47
    िंट
    0.46
     proponent
    0.45
     butyl
    0.45
     teritor
    0.45
     axle
    0.44
     município
    0.43
    Activations Density 0.010%

    No Known Activations