© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12618
    Prev
    Next
    INDEX
    Explanations

    start of quoted speech

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

    given, i, Haw, Easy, Normal, brand, tags

    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_31_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
     heatmap
    0.65
    ن
    0.56
    𝒹
    0.55
    न
    0.54
    ोहित
    0.53
    ेर
    0.52
    पाठ
    0.51
    𝓇
    0.51
    इल
    0.50
    น
    0.50
    POSITIVE LOGITS
    9
    0.54
    .,
    0.50
    ‌ای
    0.49
    I
    0.49
     a
    0.49
    8
    0.48
     I
    0.47
     an
    0.46
    Yes
    0.46
    ong
    0.46
    Activations Density 0.255%

    No Known Activations