© 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. 44488
    Prev
    Next
    INDEX
    Explanations

    computational

    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
     vem
    0.52
     konfl
    0.49
     역할을
    0.46
     komunik
    0.44
     տ
    0.44
     düz
    0.44
     ekonomi
    0.43
     demikian
    0.43
     indifer
    0.43
     tkan
    0.43
    POSITIVE LOGITS
    Bel
    0.45
    icelli
    0.45
     Niles
    0.44
    功
    0.43
     Bel
    0.43
    Chair
    0.42
    freund
    0.42
     Adik
    0.42
     друзей
    0.42
    িয়ায়
    0.41
    Activations Density 0.003%

    No Known Activations