© 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. 16-GEMMASCOPE-2-RES-262K
    7. 41337
    Prev
    Next
    INDEX
    Explanations

    EntityFramework Core

    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_16_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
    $}}
    0.73
    يا
    0.72
    ك
    0.70
    '}}
    0.66
    يد
    0.65
    ି
    0.65
    ために
    0.65
    hygine
    0.65
    ारा
    0.64
    𝘻
    0.64
    POSITIVE LOGITS
    d
    0.79
    us
    0.68
     распростра
    0.66
     appet
    0.64
     lumped
    0.64
    ۰
    0.63
     Raises
    0.63
    dW
    0.61
    ند
    0.60
     negotiated
    0.60
    Activations Density 0.000%

    No Known Activations