© 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. 3486
    Prev
    Next
    INDEX
    Explanations

    unique code or text

    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
    2.48
    6
    2.27
    8
    2.26
    9
    2.08
    req
    2.03
    sila
    2.01
    discrete
    2.01
     undefined
    2.01
     lowercase
    2.00
    FirstResponder
    1.98
    POSITIVE LOGITS
     historians
    1.39
     biographer
    1.17
    囝
    1.14
     Zoo
    1.05
     schemes
    1.03
     cartoonist
    1.02
     itinerary
    1.00
     diagrams
    1.00
    outfile
    1.00
     nets
    0.98
    Activations Density 0.042%

    No Known Activations