© 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. 46709
    Prev
    Next
    INDEX
    Explanations

    availability status

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

    English language usage and abilities

    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
    
    0.49
    臨時
    0.46
    临时
    0.46
    Appointment
    0.45
    েবের
    0.45
    ត្រូ
    0.45
    ❕
    0.44
    Approval
    0.44
    肪
    0.43
    Namun
    0.43
    POSITIVE LOGITS
     roug
    0.49
     worked
    0.48
    নারী
    0.43
    참
    0.43
    anker
    0.42
     Worked
    0.42
     वें
    0.42
     H
    0.42
     concours
    0.42
     चिह्न
    0.42
    Activations Density 0.000%

    No Known Activations