© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79455
    Prev
    Next
    INDEX
    Explanations

    always, often, decreases

    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_31_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
     первую
    0.49
     новую
    0.48
    新たな
    0.47
    <0x0D>
    0.46
     новая
    0.45
     дополнительные
    0.44
    су
    0.44
    ת
    0.44
     새로운
    0.43
    autoarima
    0.42
    POSITIVE LOGITS
     altid
    0.55
     alltid
    0.51
     Scandinavia
    0.47
     timelapse
    0.46
     anytime
    0.46
     always
    0.44
     canoeing
    0.43
     souvent
    0.43
     Ganges
    0.43
     toujours
    0.43
    Activations Density 0.008%

    No Known Activations