© 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. 120234
    Prev
    Next
    INDEX
    Explanations

    equestrian and names

    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
    🚁
    0.84
    jač
    0.74
    ።
    0.73
    ajte
    0.72
    ма
    0.70
    はよう
    0.68
     বিশ্বকাপের
    0.67
    šao
    0.67
     or
    0.66
     Оюн
    0.66
    POSITIVE LOGITS
    ne
    1.03
    r
    0.96
    an
    0.93
    la
    0.90
    m
    0.84
    on
    0.82
    list
    0.82
    d
    0.79
    liness
    0.78
    ר
    0.75
    Activations Density 0.000%

    No Known Activations