© 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. 113446
    Prev
    Next
    INDEX
    Explanations

    split the

    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
    p
    0.55
    פ
    0.50
    dv
    0.47
    ch
    0.46
    ק
    0.46
    lant
    0.43
    v
    0.43
    arach
    0.43
     Commanding
    0.43
     Tory
    0.42
    POSITIVE LOGITS
    는
    0.47
     welchen
    0.46
     которую
    0.46
     که
    0.45
     জানিয়েছে
    0.45
     يح
    0.44
     autoclave
    0.44
     perfecta
    0.43
     masukkan
    0.43
    ână
    0.43
    Activations Density 0.000%

    No Known Activations