© 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. 184357
    Prev
    Next
    INDEX
    Explanations

    felony charges, ashes, first African-American, patriotic Russians, ragged right

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

    ordered arrangements

    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
    轻松
    0.48
    ק
    0.48
    리
    0.47
    로
    0.45
    らえる
    0.45
    자
    0.44
    진
    0.44
    ж
    0.43
     transient
    0.43
    ע
    0.43
    POSITIVE LOGITS
     जिज्ञा
    0.55
     Nationalism
    0.49
     പ്രതിഷേധ
    0.47
     фотоап
    0.46
     imprensa
    0.46
    anguages
    0.45
     Soldiers
    0.45
     Trotsky
    0.45
     स्वातंत्र्य
    0.45
    fti
    0.43
    Activations Density 0.001%

    No Known Activations