© 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. 161304
    Prev
    Next
    INDEX
    Explanations

    money, resources, or possessions

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

    turn your ideassimple typographycold insidebring a listbold headline

    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
    رین
    0.49
     테이블
    0.49
    หรับ
    0.48
     tabletop
    0.45
     입력
    0.44
    웍
    0.44
     kali
    0.44
     출력
    0.44
     기록
    0.43
    𝄞
    0.42
    POSITIVE LOGITS
    Imm
    0.52
    AU
    0.50
     potrebbero
    0.49
    實際上
    0.49
    usi
    0.48
    atterson
    0.48
    ined
    0.47
    UM
    0.46
    ce
    0.46
    identified
    0.46
    Activations Density 0.000%

    No Known Activations