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

    Neuronpedia

    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. 142382
    Prev
    Next
    INDEX
    Explanations

    misspelling of the

    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
    an
    0.74
    in
    0.65
    as
    0.65
    es
    0.57
    p
    0.53
    ي
    0.53
     puas
    0.52
     his
    0.52
    et
    0.50
    יות
    0.50
    POSITIVE LOGITS
    ରି
    0.55
     نیٹ
    0.55
    ﻦ
    0.55
    cliffe
    0.52
    Immediate
    0.52
     geç
    0.51
    führer
    0.50
    inge
    0.50
    ifo
    0.50
     ಅಥವಾ
    0.50
    Activations Density 0.000%

    No Known Activations