© 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. 4473
    Prev
    Next
    INDEX
    Explanations

    key concepts and discussion

    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
    ⁰
    1.16
    req
    1.11
     Woll
    1.09
    ATTR
    1.07
     Receiving
    1.07
     Leop
    1.05
     minecraft
    1.05
     Collecting
    1.02
    rx
    1.02
     Jasmin
    1.00
    POSITIVE LOGITS
     and
    1.54
     ihn
    1.51
    astic
    1.44
    、
    1.38
     honom
    1.34
     agus
    1.34
     dan
    1.33
    uidas
    1.32
    chief
    1.32
     schemes
    1.27
    Activations Density 0.110%

    No Known Activations