© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 15147
    Prev
    Next
    INDEX
    Explanations

    Numbers, specific mentions, or technical terms

    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_22_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
     이야기
    0.83
    입니다
    0.81
    􀂾
    0.78
     হৃদয়
    0.78
     매출
    0.78
     Aynı
    0.77
     matchup
    0.77
    หัส
    0.75
    ॰ऍ
    0.74
    <unused2190>
    0.74
    POSITIVE LOGITS
     and
    0.91
     they
    0.84
     others
    0.81
     people
    0.80
     which
    0.77
     in
    0.74
     supposedly
    0.74
     etc
    0.73
     certain
    0.72
     workers
    0.72
    Activations Density 0.000%

    No Known Activations