© 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. 11381
    Prev
    Next
    INDEX
    Explanations

    specific names and labels

    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
     υπάρχει
    1.19
    ٩
    1.06
    ９
    1.05
    ６
    1.04
    ８
    1.04
    Requests
    1.03
     επίσης
    1.02
     डिन
    1.01
    పి
    1.00
    Ren
    1.00
    POSITIVE LOGITS
     and
    2.08
     và
    1.75
     maupun
    1.69
     \&
    1.66
    および
    1.63
     и
    1.60
     și
    1.60
    and
    1.60
     और
    1.59
     आणि
    1.58
    Activations Density 0.657%

    No Known Activations