© 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. 100944
    Prev
    Next
    INDEX
    Explanations

    cases and numbers

    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
     virg
    0.49
     vir
    0.44
     gost
    0.40
     po
    0.38
     forearm
    0.36
     VIR
    0.36
     Jamb
    0.35
     k
    0.35
     bili
    0.35
    ADER
    0.35
    POSITIVE LOGITS
     حالة
    0.44
     சுண்ணாம்பு
    0.44
    initState
    0.41
    ifikasi
    0.40
    Makes
    0.39
    CBD
    0.39
    ისთვის
    0.39
    hehi
    0.39
    idelijk
    0.39
    ್ಯ
    0.38
    Activations Density 0.017%

    No Known Activations