© 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. 3699
    Prev
    Next
    INDEX
    Explanations

    subtle manipulation and interaction

    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
    Rüyada
    1.38
    смотреть
    1.34
    وء
    1.30
    票
    1.20
     rocker
    1.20
    繋がりたい
    1.19
     blevet
    1.17
    iture
    1.14
    がき
    1.14
    馊
    1.13
    POSITIVE LOGITS
     supre
    2.23
    amom
    2.15
    boxyl
    2.12
    pios
    2.06
     pavatt
    2.04
    rugated
    2.04
     Difer
    1.97
     deont
    1.93
    شك
    1.93
    othing
    1.93
    Activations Density 0.093%

    No Known Activations