© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2768
    Prev
    Next
    INDEX
    Explanations

    no constraints or guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
     하나의
    0.87
     সত্যিকার
    0.82
    第一題
    0.81
    ផ្គ
    0.80
     efficiently
    0.80
     unknow
    0.79
     replete
    0.79
    ជាក់
    0.78
    မယ်
    0.78
     kaleidoscopic
    0.77
    POSITIVE LOGITS
     żad
    1.14
     except
    1.05
    任何
    1.04
    any
    0.97
    任何人
    0.96
     whatsoever
    0.95
    丝毫
    0.94
     ningún
    0.93
    except
    0.93
     никаких
    0.90
    Activations Density 0.375%

    No Known Activations