© 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-262K
    7. 165532
    Prev
    Next
    INDEX
    Explanations

    fresh product, !!! thanks, a lucrative

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

    Google Cloud services

    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_262k_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
    Indonesia
    0.54
    Jakarta
    0.51
    蛐
    0.50
    Bangladesh
    0.49
    豳
    0.46
    Những
    0.46
    álló
    0.45
    Pakistan
    0.45
    霭
    0.45
    Một
    0.44
    POSITIVE LOGITS
     втра
    0.49
     damning
    0.45
     ہر
    0.44
    ustain
    0.43
     매
    0.41
     LSU
    0.40
     via
    0.40
     uncanny
    0.40
     disastrous
    0.39
     ido
    0.39
    Activations Density 0.001%

    No Known Activations