© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 4465
    Prev
    Next
    INDEX
    Explanations

    environment configuration

    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
     in
    1.23
     are
    1.22
     готови
    1.13
    的
    1.12
     ovat
    1.10
    ará
    1.05
    ١
    1.02
    1
    1.01
    ação
    1.00
     consola
    1.00
    POSITIVE LOGITS
    0
    1.55
    ad
    1.49
    and
    1.45
    it
    1.40
    at
    1.36
    ט
    1.34
    <0x80>
    1.34
    ?
    1.32
    ین
    1.26
    ၀
    1.25
    Activations Density 0.032%

    No Known Activations