© 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. 22-GEMMASCOPE-2-RES-262K
    7. 6091
    Prev
    Next
    INDEX
    Explanations

    codes and classifications

    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_22_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
     antire
    0.86
     セミ
    0.76
     المسافه
    0.76
     fibrils
    0.74
     Inquisition
    0.74
     Kurt
    0.74
     ∆
    0.72
    孃
    0.72
    medskip
    0.71
     Reformed
    0.70
    POSITIVE LOGITS
    8
    0.84
    9
    0.82
    7
    0.74
    6
    0.72
    Numbers
    0.71
    0.70
    4
    0.66
    5
    0.63
    反映
    0.63
     ಸಂಖ್ಯ
    0.61
    Activations Density 0.066%

    No Known Activations