© 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. 1041
    Prev
    Next
    INDEX
    Explanations

    reduce costs

    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
     Opin
    1.43
    ائم
    1.41
    culis
    1.36
     Mujer
    1.31
    mati
    1.30
     بخير
    1.29
     pozitiv
    1.26
    鲤
    1.25
     positif
    1.24
     positive
    1.24
    POSITIVE LOGITS
     costs
    2.35
    costs
    2.31
     hassles
    2.20
    手間
    2.20
     Costs
    2.19
     COSTS
    2.15
     costly
    2.15
     cumbersome
    2.12
     tedious
    2.08
     expense
    2.07
    Activations Density 1.678%

    No Known Activations