© 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. 30322
    Prev
    Next
    INDEX
    Explanations

    named places and their descriptors

    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
    bs
    0.47
    ts
    0.47
    g
    0.46
    es
    0.45
    ai
    0.45
    ss
    0.44
     gode
    0.43
    氯
    0.43
    ag
    0.43
    os
    0.42
    POSITIVE LOGITS
     horrors
    0.43
    ﮑ
    0.42
     njeg
    0.41
    ायल
    0.40
     էր
    0.40
    Кла
    0.40
    了他的
    0.40
    ྃ
    0.38
     그의
    0.37
     Adası
    0.37
    Activations Density 0.020%

    No Known Activations