© 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. 53-GEMMASCOPE-2-RES-262K
    7. 18969
    Prev
    Next
    INDEX
    Explanations

    1

    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_53_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
    𝓀
    0.80
     actriz
    0.79
     interacción
    0.74
     ámbito
    0.72
    푅
    0.71
     diámetro
    0.71
     çağ
    0.71
    础
    0.71
    휋
    0.70
    ᱔
    0.70
    POSITIVE LOGITS
    ส
    1.53
    ค
    1.43
    การ
    1.40
    และ
    1.38
    ข
    1.38
    ป
    1.37
    แ
    1.37
    ที่
    1.36
    ใน
    1.36
     ป
    1.36
    Activations Density 0.017%

    No Known Activations