© 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. 218950
    Prev
    Next
    INDEX
    Explanations

    in with

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

    gram to mole ratio

    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
    髡
    0.53
     kurzen
    0.49
    ież
    0.49
     escolar
    0.47
     Manu
    0.47
    Manu
    0.47
     empie
    0.47
    лянчук
    0.47
    栤
    0.46
     völl
    0.46
    POSITIVE LOGITS
     within
    0.56
    ↵↵
    0.55
    more
    0.53
    cot
    0.53
    within
    0.50
    ratio
    0.50
    matter
    0.50
    locations
    0.49
    ridges
    0.48
    th
    0.48
    Activations Density 0.000%

    No Known Activations