© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14876
    Prev
    Next
    INDEX
    Explanations

    abbreviations and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
     legislate
    1.18
     propriet
    0.98
     gerekli
    0.97
    ાઓ
    0.97
    ির
    0.96
    u
    0.96
    गोल
    0.93
    am
    0.92
     Бог
    0.91
     التص
    0.91
    POSITIVE LOGITS
    “…
    1.16
    ﻓ
    1.08
     “…
    1.07
    $,
    1.06
    ﺗ
    1.06
     appunto
    1.06
    “(
    1.05
    ﺧ
    1.03
     के
    1.02
     धूल
    1.02
    Activations Density 0.004%

    No Known Activations