© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1236
    Prev
    Next
    INDEX
    Explanations

    list of options or questions

    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_17_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
    uja
    1.32
    esan
    1.31
    inese
    1.31
    ıc
    1.26
    aly
    1.24
    erah
    1.22
    ial
    1.22
    ം
    1.20
    iciones
    1.19
    owania
    1.19
    POSITIVE LOGITS
    ?.
    2.43
    ?!?
    2.42
    ؟.
    2.19
    ؟
    2.09
    ????
    2.09
    ؟؟
    2.07
    !?
    2.06
    ????????
    2.03
    ?!?!
    1.98
    ?
    1.97
    Activations Density 0.486%

    No Known Activations