© 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. 8013
    Prev
    Next
    INDEX
    Explanations

    disclaimers about information

    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
     marginalised
    1.95
     prioritise
    1.94
     bespoke
    1.86
     favours
    1.83
    💸
    1.82
     personalisation
    1.81
     🥰
    1.80
     underpinned
    1.73
    🥰
    1.73
    🏏
    1.72
    POSITIVE LOGITS
    instructor
    1.80
     instructor
    1.71
     azi
    1.71
     Instructor
    1.67
    Instructor
    1.61
    jut
    1.60
     επα
    1.58
     stockholder
    1.57
     arit
    1.56
     leer
    1.55
    Activations Density 0.053%

    No Known Activations