© 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. 31-GEMMASCOPE-2-RES-262K
    7. 52087
    Prev
    Next
    INDEX
    Explanations

    groups and clusters

    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
     percib
    0.50
     >>=
    0.46
     lamps
    0.45
     aisl
    0.44
     nen
    0.43
     ampli
    0.42
     bookcases
    0.41
    なく
    0.40
    ﺍ
    0.40
     empower
    0.40
    POSITIVE LOGITS
    .",[
    0.45
     задачу
    0.45
     समूहों
    0.44
    imely
    0.43
     развития
    0.43
    riminate
    0.42
     स्टेटस
    0.42
    Groups
    0.41
     माहित
    0.41
     кому
    0.41
    Activations Density 0.000%

    No Known Activations