© 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. 64719
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    manager.yml, prometheus

    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
    O
    0.53
    0
    0.47
    сле
    0.47
    зе
    0.47
    Orientation
    0.47
    icult
    0.46
    ich
    0.45
    Control
    0.45
     Queer
    0.45
    е
    0.45
    POSITIVE LOGITS
     całej
    0.55
     firmas
    0.49
    ကာ
    0.49
    巩
    0.49
     kesel
    0.46
     testigo
    0.46
     महाराष्ट
    0.46
     sinal
    0.46
     rique
    0.46
     jueces
    0.46
    Activations Density 0.000%

    No Known Activations