© 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. 15616
    Prev
    Next
    INDEX
    Explanations

    point of origin

    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
    ურთი
    0.64
    ཊ
    0.53
    蝼
    0.53
    нным
    0.52
     ascribe
    0.52
    实质
    0.50
     чрез
    0.50
     overestimate
    0.49
     resist
    0.49
     знаете
    0.48
    POSITIVE LOGITS
     STATION
    0.69
     From
    0.68
     from
    0.68
     ini
    0.68
     FROM
    0.68
     från
    0.67
     stazione
    0.66
    จ
    0.65
     och
    0.63
     station
    0.62
    Activations Density 0.045%

    No Known Activations