© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 2901
    Prev
    Next
    INDEX
    Explanations

    .py, .cache, .button

    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
    to
    0.88
     hypothes
    0.88
    0.79
     desenvolv
    0.72
     presente
    0.71
    楲
    0.66
     (
    0.65
     reorgan
    0.65
     galaxies
    0.64
    ।
    0.63
    POSITIVE LOGITS
    ли
    1.28
    ق
    1.09
    ために
    1.03
    ي
    1.02
    ד
    0.93
    ך
    0.93
    Y
    0.92
    த்தில்
    0.92
    िंग
    0.91
    ח
    0.91
    Activations Density 0.532%

    No Known Activations