© 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. 31-GEMMASCOPE-2-RES-262K
    7. 92765
    Prev
    Next
    INDEX
    Explanations

    related/similarities/help

    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_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
    Throttle
    0.42
    ക്
    0.40
    િય
    0.40
     régl
    0.39
    Dirt
    0.38
    ;:
    0.38
     اسپ
    0.38
    लर
    0.38
     plástico
    0.38
     cứ
    0.38
    POSITIVE LOGITS
    inni
    0.51
     mackerel
    0.50
    <0x0B>
    0.48
    ೆಂದು
    0.45
     poncho
    0.44
     theyre
    0.44
    ोस
    0.43
    osha
    0.43
     Translations
    0.43
     SHALL
    0.43
    Activations Density 0.014%

    No Known Activations