© 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. 174165
    Prev
    Next
    INDEX
    Explanations

    successful, taught, significant

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

    application portfolio, whatsapp reply

    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
    ◹
    0.53
    ந்தார்
    0.47
    裴
    0.47
     ശിഷ്യ
    0.46
    漢
    0.45
    过了
    0.44
    竑
    0.43
    博士
    0.43
    輔
    0.43
    Fiber
    0.42
    POSITIVE LOGITS
     Importantly
    0.49
    eqa
    0.47
    lal
    0.47
     ByteBuffer
    0.46
    tiktok
    0.46
    ionate
    0.46
     sớm
    0.46
     नाव
    0.45
    az
    0.45
     अंश
    0.45
    Activations Density 0.001%

    No Known Activations