© 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. 119516
    Prev
    Next
    INDEX
    Explanations

    radiologist, psychologist, collaborator

    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
     செல்ல
    0.51
    -/
    0.50
    دود
    0.49
    ASDW
    0.48
    LOADING
    0.47
    ersburg
    0.47
    BCD
    0.47
    投注
    0.46
     codice
    0.46
    ehl
    0.45
    POSITIVE LOGITS
    자의
    0.64
    ภาพ
    0.63
    ма
    0.59
    ം
    0.57
    मा
    0.56
    ক
    0.56
    ль
    0.55
    ম
    0.55
    މ
    0.55
     bravery
    0.55
    Activations Density 0.000%

    No Known Activations