© 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. 202662
    Prev
    Next
    INDEX
    Explanations

    legal phrases or clauses

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

    length measurements

    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
    corso
    0.50
    नोई
    0.47
    ございました
    0.43
    ڎ
    0.42
    හා
    0.42
    gha
    0.42
    ვლი
    0.42
    course
    0.41
    ioutil
    0.41
    pload
    0.41
    POSITIVE LOGITS
    ’?
    0.44
    סטי
    0.44
    的最佳
    0.43
    ？
    0.42
     commutation
    0.40
     familles
    0.40
    ryt
    0.39
     darwin
    0.39
     telef
    0.39
     Cables
    0.39
    Activations Density 0.001%

    No Known Activations