© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4061
    Prev
    Next
    INDEX
    Explanations

    changes in updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
     svolge
    0.74
     wechsel
    0.66
     hond
    0.65
     zamknię
    0.65
     חו
    0.64
    jaa
    0.64
     sj
    0.63
    𝗆
    0.63
    虛
    0.63
    ისუფ
    0.63
    POSITIVE LOGITS
    幅度
    1.01
     made
    0.97
    cations
    0.88
    made
    0.85
    alupe
    0.82
     apport
    0.78
     جذر
    0.77
    Big
    0.77
     사항
    0.76
     effected
    0.76
    Activations Density 0.301%

    No Known Activations