© 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. 168952
    Prev
    Next
    INDEX
    Explanations

    curriculum, areas, Pike, dish, reader, permeates

    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
    é
    0.58
    as
    0.53
     of
    0.52
    м
    0.50
     innocent
    0.49
    m
    0.47
    en
    0.46
    io
    0.46
     Interpreter
    0.46
     Innoc
    0.46
    POSITIVE LOGITS
     foreclose
    0.47
     συ
    0.45
    {}\
    0.45
    ettings
    0.44
    하겠습니다
    0.43
     setores
    0.43
    ToLower
    0.43
     sunroof
    0.42
    ){}
    0.42
    驱
    0.42
    Activations Density 0.000%

    No Known Activations