© 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. 7606
    Prev
    Next
    INDEX
    Explanations

    of the most

    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
    )((
    2.14
    thing
    2.11
    BODY
    2.07
    THING
    2.06
    }((
    2.05
    ianz
    2.00
     tuple
    1.96
    ]->
    1.95
     stuff
    1.92
    ข่าว
    1.91
    POSITIVE LOGITS
     many
    2.31
     several
    2.09
     few
    1.96
     only
    1.96
     countless
    1.95
    many
    1.94
     pocas
    1.91
     numerous
    1.88
     muitos
    1.88
    several
    1.84
    Activations Density 0.077%

    No Known Activations