© 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. 31-GEMMASCOPE-2-RES-262K
    7. 78895
    Prev
    Next
    INDEX
    Explanations

    fine-tuning, linking, or describing creative content

    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_31_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
    क
    0.47
    き
    0.44
    inals
    0.43
    accordo
    0.43
    물의
    0.42
    ichloro
    0.42
    visions
    0.42
    illum
    0.42
    Z
    0.42
    वास
    0.42
    POSITIVE LOGITS
     Talend
    0.48
     раза
    0.48
     Screenshots
    0.47
     Newtonsoft
    0.46
     skillset
    0.46
     OneDrive
    0.45
     predecess
    0.45
     CoA
    0.44
     THIS
    0.44
     Desktop
    0.44
    Activations Density 0.017%

    No Known Activations