© 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. 31-GEMMASCOPE-2-RES-65K
    7. 47868
    Prev
    Next
    INDEX
    Explanations

    focus on key metrics

    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_65k_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
    pués
    0.51
     நிர
    0.48
    تها
    0.45
     irmão
    0.45
    новения
    0.45
     '../
    0.45
     adquirido
    0.44
     പഴയ
    0.44
     большого
    0.43
    сто
    0.43
    POSITIVE LOGITS
    T
    0.51
     ruh
    0.48
     Cutting
    0.48
    cutting
    0.46
     Schluss
    0.44
     ETA
    0.44
    kor
    0.44
    ON
    0.44
     Worcester
    0.44
    rfc
    0.43
    Activations Density 0.011%

    No Known Activations