© 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. 12895
    Prev
    Next
    INDEX
    Explanations

    response in json

    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
     môže
    1.49
    may
    1.45
     मालिक
    1.43
    might
    1.42
    ḫ
    1.40
    fireFlower
    1.40
    puede
    1.39
    lava
    1.35
    ग्गा
    1.35
    ರನ್ನು
    1.32
    POSITIVE LOGITS
     purposes
    1.62
     sake
    1.53
     betterment
    1.41
     posterity
    1.40
    :
    1.26
     starters
    1.16
    เท่านั้น
    1.13
    :-
    1.12
    :*
    1.12
    rest
    1.10
    Activations Density 0.890%

    No Known Activations