© 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. 7650
    Prev
    Next
    INDEX
    Explanations

    more deterministic or creative

    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
     micrograms
    1.68
    Gb
    1.67
    obarbital
    1.65
     macrom
    1.63
     billiard
    1.57
     pathophys
    1.57
     ultram
    1.55
     ¹
    1.55
     cyclohex
    1.53
     Pentium
    1.53
    POSITIVE LOGITS
     лінії
    1.34
    线的
    1.28
    isses
    1.25
     можливо
    1.24
     linea
    1.24
    ят
    1.22
    rimos
    1.22
    зик
    1.21
    還可以
    1.20
     vrt
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.