© 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. 14987
    Prev
    Next
    INDEX
    Explanations

    actions, options, or configurations

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

    explicitly specify

    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
     পদ্ধ
    0.40
    oclaw
    0.40
    gallery
    0.38
     그대로
    0.38
    getStartState
    0.37
     Pastel
    0.37
     Unless
    0.37
    リ
    0.37
     সবচেয়ে
    0.36
    azure
    0.36
    POSITIVE LOGITS
     during
    0.54
     durante
    0.53
     opting
    0.53
     voluntarily
    0.52
     optionally
    0.52
     opción
    0.51
    During
    0.50
     지정
    0.50
     request
    0.49
     explicitly
    0.49
    Activations Density 0.094%

    No Known Activations