© 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. 28623
    Prev
    Next
    INDEX
    Explanations

    information content, stack, spirit, time

    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
     yếu
    0.47
    妧
    0.46
     negócio
    0.45
     主要
    0.45
     puestos
    0.44
     如何
    0.43
    ರ
    0.43
    <0xB9>
    0.43
     Đúng
    0.42
    rvGroup
    0.42
    POSITIVE LOGITS
    ที่มี
    0.44
    2
    0.41
    стых
    0.41
     unsurpassed
    0.41
     varios
    0.40
     revived
    0.39
     twenty
    0.39
     rekind
    0.39
     unmatched
    0.38
     maintained
    0.38
    Activations Density 0.005%

    No Known Activations