© 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. 42057
    Prev
    Next
    INDEX
    Explanations

    sales figures and data

    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
     دور
    0.47
     yolu
    0.45
    𒋗
    0.44
     يمكن
    0.42
     leaderboard
    0.41
     leaching
    0.40
    шат
    0.40
     થઈ
    0.40
     حسین
    0.40
     realización
    0.40
    POSITIVE LOGITS
     Metropolitana
    0.40
     ;-)
    0.40
     beteg
    0.39
     Checked
    0.37
    ';
    0.37
    ]}{
    0.36
     Ordinance
    0.36
     Dag
    0.36
    였습니다
    0.36
    ')
    0.35
    Activations Density 0.003%

    No Known Activations