© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 7636
    Prev
    Next
    INDEX
    Explanations

    list items or section titles

    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
    oarthritis
    0.49
    an
    0.47
    otard
    0.44
     su
    0.44
     Landkreis
    0.44
    itiers
    0.43
     ย
    0.43
    oe
    0.43
    ر
    0.43
    邰
    0.43
    POSITIVE LOGITS
     económ
    0.50
    ным
    0.48
     presup
    0.45
     académica
    0.44
    ㅝ
    0.43
    地方
    0.42
     nasional
    0.42
     geográfica
    0.41
    ﻬ
    0.41
     pengetahuan
    0.40
    Activations Density 0.005%

    No Known Activations