© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3484
    Prev
    Next
    INDEX
    Explanations

    `@` symbols

    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
     Quin
    1.29
     fetal
    1.28
    Quin
    1.25
     instruction
    1.15
    韶
    1.15
     elementary
    1.14
     puer
    1.13
     wave
    1.13
     lead
    1.11
     delta
    1.09
    POSITIVE LOGITS
    @-
    2.12
    @
    2.05
     @
    1.97
     @_
    1.94
    :@
    1.62
    ,@
    1.61
    @"
    1.61
    (@
    1.60
    }@
    1.56
    @(
    1.56
    Activations Density 0.050%

    No Known Activations