© 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. 244185
    Prev
    Next
    INDEX
    Explanations

    business plan perspective

    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
     Herd
    0.49
    粖
    0.47
     Joni
    0.47
     Интере
    0.45
    ారు
    0.45
    埆
    0.45
    䯩
    0.45
    誤差
    0.45
    ង្
    0.44
    াকের
    0.44
    POSITIVE LOGITS
     나
    0.55
     가
    0.46
     암
    0.46
     علیکم
    0.45
     지
    0.42
    PN
    0.42
     legit
    0.42
    STAGE
    0.42
    legte
    0.41
    PY
    0.41
    Activations Density 0.003%

    No Known Activations