© 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. 2427
    Prev
    Next
    INDEX
    Explanations

    construct()

    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
    ра
    0.48
    ها
    0.45
     Loki
    0.44
    rik
    0.42
    ired
    0.42
     reformation
    0.41
    ush
    0.41
    յ
    0.41
     صغير
    0.40
    螅
    0.40
    POSITIVE LOGITS
    n
    0.61
     Consultado
    0.56
    ン
    0.55
     постро
    0.54
     proline
    0.53
     on
    0.53
     Sociedad
    0.52
     Grupo
    0.51
     নিজে
    0.51
    PHIA
    0.51
    Activations Density 0.000%

    No Known Activations