© 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. 5469
    Prev
    Next
    INDEX
    Explanations

    absolutely fantastic

    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
    使用
    0.39
     weaker
    0.38
    ｛
    0.36
     superficially
    0.36
    😟
    0.36
     impair
    0.35
     poorly
    0.35
     saddened
    0.35
    $/.
    0.35
     weakly
    0.34
    POSITIVE LOGITS
     તમને
    0.48
     naprawdę
    0.47
     Magic
    0.47
     👌
    0.46
     😍
    0.46
     magia
    0.46
     extravaganza
    0.45
     classy
    0.45
     perfection
    0.44
     foodie
    0.44
    Activations Density 0.301%

    No Known Activations