© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2866
    Prev
    Next
    INDEX
    Explanations

    in detail

    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
     Sub
    1.28
     Pet
    1.25
     Ter
    1.21
     Post
    1.21
     T
    1.18
     Trans
    1.16
     Pre
    1.11
     Norm
    1.08
     Cross
    1.07
     Key
    1.05
    POSITIVE LOGITS
    쥴
    1.44
    CLUD
    1.32
    quinazoline
    1.29
    umia
    1.26
    agio
    1.23
     innovación
    1.21
     Chavan
    1.20
     аппарат
    1.20
     madison
    1.19
     Cupertino
    1.18
    Activations Density 0.045%

    No Known Activations