© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10964
    Prev
    Next
    INDEX
    Explanations

    definition and meaning of words

    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
    ỷ
    1.70
    anager
    1.61
    чо
    1.61
     ske
    1.55
     electrom
    1.53
    اريات
    1.53
    arten
    1.53
     torchvision
    1.49
    setLevel
    1.45
    的热
    1.45
    POSITIVE LOGITS
     pronouncing
    2.29
     pronunciation
    2.20
     pron
    2.04
    ು
    1.92
     pronunci
    1.90
     pronounce
    1.78
     consonants
    1.74
     اللغه
    1.74
     diph
    1.72
    ฺ
    1.69
    Activations Density 0.070%

    No Known Activations