© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 99020
    Prev
    Next
    INDEX
    Explanations

    foreign terms and origins

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

    building from scratch

    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
    q
    0.49
    ogliamo
    0.47
    ardust
    0.43
    žne
    0.42
    が出る
    0.42
    ブラ
    0.41
    出す
    0.40
    ধন
    0.40
    ීන්
    0.40
    čić
    0.40
    POSITIVE LOGITS
     soggetto
    0.50
    砳
    0.50
     soggetti
    0.49
     antigu
    0.49
     හ
    0.47
     courants
    0.46
     Choisissez
    0.46
     aguda
    0.45
     aiutare
    0.45
     undertake
    0.45
    Activations Density 0.000%

    No Known Activations