© 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. 4314
    Prev
    Next
    INDEX
    Explanations

    be mindful and great opportunity

    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
    7
    1.52
    9
    1.41
    6
    1.39
    5
    1.35
    4
    1.34
    3
    1.27
     ThinQ
    1.23
    8
    1.23
     complémentaires
    1.19
     موجوده
    1.19
    POSITIVE LOGITS
     processions
    1.19
    蜞
    1.10
     Expos
    1.10
    plo
    1.08
    踏
    1.07
    lde
    1.06
    itus
    1.06
     Trips
    1.05
     Cro
    1.03
     امتحان
    1.03
    Activations Density 0.089%

    No Known Activations