© 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. 7192
    Prev
    Next
    INDEX
    Explanations

    theory and its relations

    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
     tranquillity
    1.65
    programme
    1.60
    GORITHM
    1.50
    StateManager
    1.48
    ىن
    1.47
     (_.
    1.43
    indul
    1.39
    dyna
    1.39
     realise
    1.37
     optimise
    1.36
    POSITIVE LOGITS
    /
    1.65
     stacks
    1.61
    +
    1.59
     first
    1.56
     +
    1.54
     roughly
    1.46
     "
    1.46
    first
    1.46
     nearly
    1.44
    @
    1.44
    Activations Density 0.063%

    No Known Activations