© 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. 6179
    Prev
    Next
    INDEX
    Explanations

    primes are

    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
     at
    0.90
     ten
    0.84
     most
    0.84
    ,
    0.82
     van
    0.81
     under
    0.79
     island
    0.77
     Ten
    0.77
     San
    0.77
     on
    0.76
    POSITIVE LOGITS
    Compet
    0.86
    𒌋
    0.82
    Aslamualaikum
    0.81
     competición
    0.81
     ऑल
    0.81
     डिजी
    0.80
    隧
    0.80
    resTmp
    0.79
    듑
    0.79
    𒄿
    0.78
    Activations Density 0.000%

    No Known Activations