© 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. 41903
    Prev
    Next
    INDEX
    Explanations

    discussing difficult or impossible predictions

    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
    മുണ്ട്
    0.46
     بهره
    0.44
     Weinberg
    0.42
    кті
    0.42
    幟
    0.41
     автомоби
    0.41
    连衣裙
    0.41
     तुम
    0.40
     tellus
    0.40
    巿
    0.40
    POSITIVE LOGITS
    setTimeout
    0.46
     sooner
    0.40
     unsuccessful
    0.39
     exclamation
    0.39
     desperately
    0.38
    instructions
    0.38
     removal
    0.37
     lessened
    0.37
    thunder
    0.37
     damage
    0.36
    Activations Density 0.002%

    No Known Activations