© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138663
    Prev
    Next
    INDEX
    Explanations

    God and Christ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    왕
    0.39
    urses
    0.38
    гада
    0.37
     tilt
    0.37
     tins
    0.37
     motifs
    0.37
     powdery
    0.36
     moieties
    0.35
    oon
    0.35
    Bul
    0.35
    POSITIVE LOGITS
     जमानत
    0.41
    淉
    0.41
    lenül
    0.39
    liness
    0.37
    žeme
    0.36
    čnost
    0.36
    ⟤
    0.36
     मदत
    0.35
    լ
    0.35
     शुरुआ
    0.35
    Activations Density 0.002%

    No Known Activations