© 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. 12-GEMMASCOPE-2-RES-16K
    7. 5468
    Prev
    Next
    INDEX
    Explanations

    placeholders following "your"

    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
    mıştı
    2.01
     historian
    1.91
     periodista
    1.88
     investigador
    1.80
     เวอร์
    1.78
     vicepresidente
    1.74
    ués
    1.73
     '{
    1.72
     "{
    1.72
     arquivo
    1.70
    POSITIVE LOGITS
     Minimum
    1.48
     Ideal
    1.39
     Maximum
    1.39
    Minimum
    1.35
     isteyen
    1.32
     ideal
    1.30
    Prefer
    1.30
    Maximum
    1.27
    Price
    1.25
     ideale
    1.25
    Activations Density 0.222%

    No Known Activations