© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23857
    Prev
    Next
    INDEX
    Explanations

    MSI, Debian, Audio, MTR, pacman

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝘰
    0.46
    韫
    0.46
     йөк
    0.46
     Ō
    0.43
     Гинд
    0.43
    𝚘
    0.43
    клары
    0.42
    丷
    0.42
     یا
    0.42
     ойной
    0.42
    POSITIVE LOGITS
    ui
    0.48
     motorway
    0.47
     judicial
    0.46
     tej
    0.46
     polity
    0.45
     M
    0.44
    «
    0.44
    எம்
    0.44
     MSU
    0.44
     m
    0.44
    Activations Density 0.180%

    No Known Activations