© 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. 40-GEMMASCOPE-2-RES-262K
    7. 111457
    Prev
    Next
    INDEX
    Explanations

    Floor modification and crime reduction

    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_40_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
    説
    0.42
    BUFFER
    0.40
    雰
    0.39
    作出
    0.38
     faisons
    0.38
    π
    0.36
    ິ
    0.35
    PayPal
    0.35
     бекер
    0.35
    EndY
    0.35
    POSITIVE LOGITS
     রোল
    0.44
     ";
    0.41
     Instead
    0.39
    crest
    0.39
    rafts
    0.39
    rupa
    0.39
    دە
    0.38
     प्रद
    0.38
    ựa
    0.38
    dex
    0.38
    Activations Density 0.001%

    No Known Activations