© 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. 40-GEMMASCOPE-2-RES-262K
    7. 137296
    Prev
    Next
    INDEX
    Explanations

    water containers

    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_40_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
    ಿದರೆ
    0.46
    焚
    0.42
     maî
    0.42
    ંત
    0.41
     становника
    0.40
    בת
    0.40
    вость
    0.40
    뜩
    0.40
    ьте
    0.39
    ピアノ
    0.39
    POSITIVE LOGITS
     canteen
    0.87
     flask
    0.82
     flasks
    0.80
     Flask
    0.73
     bottles
    0.70
     bladder
    0.66
    flask
    0.66
     bottle
    0.66
     Bottle
    0.61
     Bottles
    0.60
    Activations Density 0.016%

    No Known Activations