© 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. 16-GEMMASCOPE-2-RES-262K
    7. 9556
    Prev
    Next
    INDEX
    Explanations

    straight and straighten

    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_16_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
    ק
    1.30
    л
    1.29
    ки
    1.13
    ة
    1.08
    G
    1.03
    ল
    0.98
    ك
    0.98
    ية
    0.98
    ש
    0.97
     on
    0.95
    POSITIVE LOGITS
     straight
    0.92
    ۔
    0.88
     Straight
    0.86
     methodical
    0.80
    میان
    0.78
     victimization
    0.78
     sequestration
    0.77
     나
    0.77
    िसोदिया
    0.77
     murderer
    0.76
    Activations Density 0.004%

    No Known Activations