© 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. 2491
    Prev
    Next
    INDEX
    Explanations

    legal rights and limitations

    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
     gold
    0.81
     heller
    0.70
     plano
    0.69
     individual
    0.69
     '
    0.68
     grille
    0.66
     human
    0.65
     fil
    0.64
     (
    0.63
     honest
    0.63
    POSITIVE LOGITS
    权限
    0.99
    语言
    0.99
    👷
    0.98
    żenia
    0.96
    語言
    0.96
    ślin
    0.96
    冫
    0.95
    ैन
    0.95
    ቦች
    0.93
    ídio
    0.91
    Activations Density 0.001%

    No Known Activations