© 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. 28302
    Prev
    Next
    INDEX
    Explanations

    variable outcomes

    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
    igious
    0.46
     volat
    0.46
    احنا
    0.44
     Frankfort
    0.43
     Converse
    0.43
    Ἰ
    0.43
    Ꮏ
    0.42
    ﻌ
    0.41
    एशन
    0.40
    गारी
    0.40
    POSITIVE LOGITS
    creates
    0.55
     organizes
    0.51
    re
    0.49
     traverses
    0.48
     Jednak
    0.46
     ระยะ
    0.45
     identifies
    0.45
     specifies
    0.45
     дает
    0.45
     allocates
    0.45
    Activations Density 0.008%

    No Known Activations