© 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. 15-GEMMASCOPE-2-RES-16K
    7. 5882
    Prev
    Next
    INDEX
    Explanations

    necessary permissions or requirements

    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_15_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
    ».
    1.03
     based
    0.90
    |.
    0.90
    indeed
    0.89
    '.
    0.87
    >.
    0.85
     of
    0.85
    –
    0.85
    ’.
    0.85
    »،
    0.83
    POSITIVE LOGITS
     requisite
    2.93
     temer
    2.81
     capability
    2.71
    capability
    2.69
    necessary
    2.61
     necesarios
    2.59
     permesso
    2.54
     necessary
    2.53
     samme
    2.52
     mesmas
    2.50
    Activations Density 0.451%

    No Known Activations