© 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. 39920
    Prev
    Next
    INDEX
    Explanations

    well, without, pulled

    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
     promove
    0.52
    ﺪ
    0.45
     علاقوں
    0.44
     privilegio
    0.44
    🔹
    0.44
    =>{
    0.44
    ぐらい
    0.44
    পুণ
    0.43
     scheming
    0.43
    اصمة
    0.43
    POSITIVE LOGITS
     WELL
    0.44
     உட்க
    0.42
     sd
    0.40
     Well
    0.39
    LA
    0.39
    他
    0.39
    L
    0.39
     maths
    0.39
    DIS
    0.38
     yr
    0.38
    Activations Density 0.002%

    No Known Activations