© 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
    2. Gemma-3-270M
    3. 12-GEMMASCOPE-2-RES-16K
    4. 4579
    Prev
    Next
    INDEX
    Explanations

    offering or proposing

    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
     PARTIC
    1.52
     contemplation
    1.41
     revêtu
    1.40
     devenir
    1.37
    心を
    1.37
     dhad
    1.36
     $=$
    1.36
    感を
    1.35
    éraire
    1.34
    瞠
    1.33
    POSITIVE LOGITS
    推出的
    1.69
    推出了
    1.68
     выпусти
    1.61
     предлагают
    1.55
     offer
    1.54
     announce
    1.45
     anbieten
    1.43
    那边
    1.43
     देतात
    1.42
    advertise
    1.42
    Activations Density 0.644%

    No Known Activations