© 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. 140770
    Prev
    Next
    INDEX
    Explanations

    directory service, latent vectors, Bengal, desire

    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
     поведения
    0.57
    玑
    0.49
     neurologist
    0.48
    ケート
    0.48
     prendre
    0.47
     documental
    0.47
     Resultados
    0.47
     valeurs
    0.47
     obtenir
    0.46
    हित
    0.46
    POSITIVE LOGITS
    in
    0.77
    u
    0.64
    is
    0.57
    l
    0.56
    m
    0.54
    my
    0.52
    ość
    0.52
    line
    0.50
    box
    0.50
    en
    0.50
    Activations Density 0.000%

    No Known Activations