© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 33586
    Prev
    Next
    INDEX
    Explanations

    sex and sexes

    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
    ],
    0.59
    </strong>
    0.57
     シェ
    0.55
    ks
    0.54
    使用
    0.54
    centaje
    0.54
    cs
    0.53
    Values
    0.52
    abaab
    0.52
    ﺸ
    0.52
    POSITIVE LOGITS
    of
    0.80
    '
    0.68
     pár
    0.59
    έρ
    0.58
    ű
    0.57
     of
    0.55
     ਇੱਕ
    0.55
     deliberations
    0.54
     drifts
    0.54
     respir
    0.53
    Activations Density 0.005%

    No Known Activations