© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3395
    Prev
    Next
    INDEX
    Explanations

    lunch, innovative ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    lectric
    1.30
     Ashe
    1.22
    Entities
    1.18
    7
    1.16
    끽
    1.12
    wesen
    1.11
    disconnected
    1.07
    getExternal
    1.07
    8
    1.06
    ADDED
    1.06
    POSITIVE LOGITS
     timetable
    1.48
     Revision
    1.47
     planen
    1.45
     historians
    1.45
     strategist
    1.44
    revision
    1.44
     revision
    1.38
     Ramb
    1.37
    рин
    1.37
     期
    1.35
    Activations Density 0.068%

    No Known Activations