© 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. 27353
    Prev
    Next
    INDEX
    Explanations

    time in code

    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
    h
    0.68
    n
    0.66
    "=
    0.64
    konto
    0.63
    kBtu
    0.61
     inet
    0.61
    ferences
    0.59
    toluene
    0.59
    c
    0.59
    fie
    0.59
    POSITIVE LOGITS
    К
    0.83
     has
    0.81
     A
    0.74
    أ
    0.73
    자
    0.72
        
    0.70
     Может
    0.70
    ר
    0.70
    </h2>
    0.69
    Я
    0.68
    Activations Density 0.005%

    No Known Activations