© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 89625
    Prev
    Next
    INDEX
    Explanations

    pod install, index, pulse

    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
     identifik
    0.55
     Tento
    0.51
     Datenschutz
    0.51
    ichten
    0.49
    a
    0.48
    }"
    0.47
    punk
    0.46
     Type
    0.46
     formul
    0.46
     starken
    0.46
    POSITIVE LOGITS
    Charles
    0.53
    тию
    0.51
     fueling
    0.50
    ີນ
    0.50
    с
    0.49
    থমে
    0.49
     середине
    0.47
    চাল
    0.47
    Centre
    0.46
    हिनी
    0.46
    Activations Density 0.000%

    No Known Activations