© 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. 3801
    Prev
    Next
    INDEX
    Explanations

    wayfire, bit quantization

    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
     २०१
    0.71
     xrange
    0.65
     ২০১৫
    0.59
     २००
    0.54
     ২০১২
    0.53
     CrL
    0.52
    ☺
    0.52
     bibliographic
    0.52
     prostitutes
    0.50
     ২০১০
    0.50
    POSITIVE LOGITS
     metaverse
    1.10
     ২০২২
    0.96
     reimag
    0.95
     ২০২৩
    0.92
     Metaverse
    0.87
    🫶
    0.87
     Biden
    0.84
    🥹
    0.84
    TikTok
    0.84
     eSIM
    0.84
    Activations Density 0.927%

    No Known Activations