© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9715
    Prev
    Next
    INDEX
    Explanations

    both individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    larım
    0.54
    énieur
    0.52
    𝓻
    0.51
    이지만
    0.51
     бясплат
    0.50
     pilgrims
    0.50
     skute
    0.50
     ちゃっ
    0.50
     препара
    0.49
     inférieures
    0.49
    POSITIVE LOGITS
     determination
    0.43
    (
    0.42
    disable
    0.41
    सहाय
    0.40
     Sosa
    0.39
     decision
    0.39
    装
    0.38
     paints
    0.38
     radar
    0.38
    될
    0.38
    Activations Density 0.002%

    No Known Activations