© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13309
    Prev
    Next
    INDEX
    Explanations

    exit directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     ظاهر
    0.88
    ен
    0.88
    ెం
    0.87
    ו
    0.87
    曾經
    0.85
     carrying
    0.85
    证实
    0.83
     चलती
    0.83
    가
    0.81
     Carrying
    0.80
    POSITIVE LOGITS
     Wolverines
    1.10
     alfa
    1.09
     benchmarks
    1.09
     feline
    1.08
     sizzling
    1.07
     toxic
    1.05
     silky
    1.04
    <unused2027>
    1.03
     talent
    1.03
     talents
    1.02
    Activations Density 0.002%

    No Known Activations