© 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. 95739
    Prev
    Next
    INDEX
    Explanations

    kin, kids, Colorado, according

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

    @ and network addresses

    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
    辔
    0.45
    蕴
    0.45
     volto
    0.44
     Approaches
    0.43
     inim
    0.43
     영업
    0.42
     कमाई
    0.41
     JOHNSON
    0.41
     ELEMENTS
    0.41
    랑
    0.41
    POSITIVE LOGITS
    ボリューム
    0.48
    し
    0.48
    オフィス
    0.46
    メリ
    0.45
    すぐに
    0.45
    赤ちゃん
    0.45
    しっかり
    0.44
    オス
    0.44
    マ
    0.44
    クレ
    0.44
    Activations Density 0.004%

    No Known Activations