© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12165
    Prev
    Next
    INDEX
    Explanations

    sound better

    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_7_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
     hectic
    2.56
    ὰ
    2.24
     awake
    2.20
    찮
    2.18
     seep
    2.10
     bustling
    2.08
    ˃
    2.08
    awake
    2.05
     midnight
    2.04
     sultry
    2.02
    POSITIVE LOGITS
    ה
    3.45
    eing
    3.31
    े
    3.23
    ので
    3.20
    a
    3.17
    اخت
    3.07
    elem
    3.06
    ে
    3.04
    ził
    2.84
    e
    2.81
    Activations Density 0.004%

    No Known Activations