© 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. 76725
    Prev
    Next
    INDEX
    Explanations

    slopes and ups

    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
     выйти
    0.43
    平衡
    0.43
     Schro
    0.41
     equipo
    0.41
     innocuous
    0.40
     ան
    0.40
    …
    0.40
    equilibrium
    0.40
    Fourth
    0.39
     equilibrium
    0.39
    POSITIVE LOGITS
    ግሎ
    0.51
     Chester
    0.48
     maanden
    0.43
     বাংলায়
    0.43
    冭
    0.43
     चिंत
    0.42
     বাংলায়
    0.41
     César
    0.41
    阌
    0.41
    haupt
    0.41
    Activations Density 0.003%

    No Known Activations