© 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. 53-GEMMASCOPE-2-RES-262K
    7. 37245
    Prev
    Next
    INDEX
    Explanations

    words starting with "Ir"

    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_53_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
     tenor
    0.40
     судь
    0.38
     />);
    0.37
    夸
    0.34
     bestimm
    0.33
     هيك
    0.33
    millis
    0.32
     ま
    0.32
    pital
    0.32
     पहना
    0.32
    POSITIVE LOGITS
     Ir
    0.86
    Ir
    0.79
     ir
    0.76
    reversible
    0.74
    regular
    0.69
     इर
    0.68
    regardless
    0.66
     irregular
    0.65
    ritable
    0.63
    itating
    0.63
    Activations Density 0.005%

    No Known Activations