© 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. 4297
    Prev
    Next
    INDEX
    Explanations

    soft buttons or dry

    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
     모든
    0.46
     pien
    0.45
     특정
    0.45
     terrenos
    0.44
     بسیار
    0.43
     захо
    0.42
    ন
    0.42
     raya
    0.42
    킨
    0.42
     suunn
    0.42
    POSITIVE LOGITS
    heu
    0.53
    َة
    0.53
    optimal
    0.50
    ia
    0.49
    friendly
    0.49
    oxidation
    0.49
    ました
    0.48
    बंधनाच्या
    0.47
    ῃ
    0.47
    estamps
    0.46
    Activations Density 0.000%

    No Known Activations