© 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. 4042
    Prev
    Next
    INDEX
    Explanations

    researching and developing plans

    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
    TON
    0.47
     Home
    0.46
    BP
    0.46
    Boe
    0.46
    腆
    0.45
    SAT
    0.45
    SIP
    0.45
     tục
    0.45
    Ở
    0.45
     Leu
    0.44
    POSITIVE LOGITS
     brakes
    0.51
     Pacheco
    0.48
    ిత
    0.47
     څرنګ
    0.46
     materialized
    0.45
     decays
    0.45
    되었습니다
    0.44
    dbi
    0.44
     renders
    0.44
     confirms
    0.43
    Activations Density 0.000%

    No Known Activations