© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3785
    Prev
    Next
    INDEX
    Explanations

    flexibility

    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
    —“
    2.88
    —
    2.84
     "[
    2.75
     “[
    2.61
    “[
    2.60
     "'
    2.55
    )—
    2.55
     —
    2.46
    --"
    2.45
     '[
    2.44
    POSITIVE LOGITS
     equipments
    1.67
    igment
    1.47
     ocasion
    1.44
    varage
    1.44
     evidences
    1.42
     stuffs
    1.37
     leafs
    1.33
     malay
    1.31
    zzles
    1.28
     researches
    1.24
    Activations Density 0.600%

    No Known Activations