© 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-65K
    7. 52603
    Prev
    Next
    INDEX
    Explanations

    instant access and results

    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_65k_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
    ו
    0.56
    э
    0.54
    ки
    0.53
    е
    0.50
    기
    0.49
    л
    0.48
     ಡ
    0.48
    eless
    0.47
    is
    0.47
    ೋ
    0.45
    POSITIVE LOGITS
     adver
    0.47
     fistule
    0.47
     identifik
    0.47
     oldValue
    0.46
     vínculo
    0.46
     $\%
    0.46
     আদেশ
    0.46
     nostalg
    0.45
     tulang
    0.45
     recog
    0.45
    Activations Density 0.003%

    No Known Activations