© 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. 94665
    Prev
    Next
    INDEX
    Explanations

    world and rankings

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

    aggressive, static data, tangent line, superposition

    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
    曖
    0.46
    Introduction
    0.45
    暧
    0.45
    去找
    0.44
     delight
    0.43
     Delight
    0.43
     empowerment
    0.42
    -
    0.41
    ierter
    0.40
     द्वितीय
    0.40
    POSITIVE LOGITS
     đây
    0.48
     ülke
    0.47
     preocupaciones
    0.47
    Ỹ
    0.47
     ケース
    0.47
     thấm
    0.46
    ători
    0.46
     hedef
    0.46
     காங்க
    0.46
    ДИ
    0.46
    Activations Density 0.000%

    No Known Activations