© 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. 31-GEMMASCOPE-2-RES-262K
    7. 55688
    Prev
    Next
    INDEX
    Explanations

    before learning

    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
     گزینه
    0.46
    ഭ
    0.46
    सँग
    0.45
    回忆
    0.44
    दय
    0.44
    ឌ
    0.43
     थेट
    0.43
    喊
    0.43
    ampaikan
    0.42
    凌
    0.42
    POSITIVE LOGITS
     primeiro
    0.48
     scrutiny
    0.48
     dim
    0.47
     plasmids
    0.46
     genes
    0.46
     worth
    0.45
     batteries
    0.45
     monotony
    0.45
     back
    0.44
     reviewing
    0.44
    Activations Density 0.005%

    No Known Activations