© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 457
    Prev
    Next
    INDEX
    Explanations

    CIA World Factbook country links

    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
     विक्रांत
    0.83
     relief
    0.80
     వి
    0.77
     Relief
    0.76
    殤
    0.74
     MS
    0.74
    वायु
    0.74
     disarmament
    0.73
     চিত্র
    0.73
    ﺡ
    0.72
    POSITIVE LOGITS
    രിക്ക
    0.68
    ikation
    0.58
     образования
    0.58
    tywn
    0.58
     بواسط
    0.58
    镀
    0.57
     ಮಾಡ
    0.57
     싶은
    0.57
    好きな
    0.56
     සැ
    0.56
    Activations Density 0.005%

    No Known Activations