Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 565
    Prev
    Next
    INDEX
    Explanations

    building or bookshelf

    np_acts-logits-general · gemini-2.5-flash-lite

    foreign languages and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    n
    0.45
    as
    0.43
    on
    0.41
    er
    0.39
    _
    0.39
    t
    0.37
    c
    0.37
    il
    0.36
    te
    0.35
    to
    0.35
    POSITIVE LOGITS
     моём
    0.41
     ഞാൻ
    0.36
     așa
    0.35
    ﻚ
    0.35
     ผม
    0.35
     horribly
    0.35
     unsightly
    0.35
     लड़की
    0.34
     giorni
    0.33
     abruptly
    0.33
    Activations Density 0.000%

    No Known Activations