© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4610
    Prev
    Next
    INDEX
    Explanations

    Oh, this

    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_13_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
     চরম
    1.49
    炷
    1.41
    чина
    1.40
    膵
    1.39
     ऐसा
    1.36
    ixar
    1.33
    cei
    1.31
     শিশু
    1.31
     Drav
    1.30
    Ln
    1.29
    POSITIVE LOGITS
     पक्षा
    1.28
     availability
    1.25
     limitation
    1.18
    뺄
    1.18
     disponibilité
    1.14
     limitations
    1.11
     제한
    1.07
    availability
    1.07
     limit
    1.04
    ותר
    1.03
    Activations Density 0.009%

    No Known Activations