© 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. 31-GEMMASCOPE-2-RES-16K
    7. 4572
    Prev
    Next
    INDEX
    Explanations

    exclusion of visual references or apologizing

    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_31_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
    리
    0.43
    认为
    0.41
    行为
    0.41
    าส
    0.40
    自身的
    0.40
    ้ว
    0.39
    жли
    0.39
    应
    0.39
    遭受
    0.39
    उनकी
    0.39
    POSITIVE LOGITS
     pero
    0.47
     plus
    0.47
     لكن
    0.46
     aber
    0.46
     but
    0.44
     umfass
    0.44
     West
    0.44
     Zudem
    0.43
     supplemented
    0.42
     zudem
    0.42
    Activations Density 0.650%

    No Known Activations