© 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. 2637
    Prev
    Next
    INDEX
    Explanations

    not ___, except ___

    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
    ২
    1.68
    ۸
    1.63
    ৩
    1.62
    ８
    1.55
    ৬
    1.53
    ९
    1.51
    ८
    1.49
    ৪
    1.48
    ৭
    1.45
    २
    1.45
    POSITIVE LOGITS
     nitrogen
    1.48
     ble
    1.47
     annihil
    1.45
     dont
    1.44
     wedges
    1.40
     susceptible
    1.39
     stomp
    1.38
     foil
    1.38
     thicken
    1.35
    dard
    1.32
    Activations Density 0.002%

    No Known Activations