© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4633
    Prev
    Next
    INDEX
    Explanations

    javascript code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     analysed
    1.66
     analysing
    1.55
     islets
    1.54
     analyse
    1.48
    spots
    1.44
     emphasises
    1.43
     emphasised
    1.42
    塾
    1.39
     interrog
    1.39
     analyses
    1.38
    POSITIVE LOGITS
    arlene
    1.52
     zipcode
    1.45
    geordnet
    1.44
    🇺
    1.44
     NASCAR
    1.40
    agrave
    1.39
     можли
    1.38
    גיע
    1.37
     Etsy
    1.35
     Terri
    1.35
    Activations Density 0.089%

    No Known Activations