© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11064
    Prev
    Next
    INDEX
    Explanations

    very followed by intensifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    ด
    2.71
    рного
    2.54
    रक
    2.35
    ocrats
    2.34
    <0x87>
    2.31
    elni
    2.22
    ন
    2.18
     sedimentation
    2.18
    рный
    2.15
    र
    2.15
    POSITIVE LOGITS
     throwIf
    1.85
    看護
    1.84
    typeparam
    1.81
     στιγμή
    1.78
     kész
    1.78
    െയുള്ള
    1.76
    ering
    1.75
    ும்பி
    1.71
    showMessage
    1.70
     Regards
    1.70
    Activations Density 0.030%

    No Known Activations