© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8656
    Prev
    Next
    INDEX
    Explanations

    going into detail

    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_13_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
    not
    2.30
    lllll
    2.22
    ের
    2.08
     not
    2.07
    u
    2.05
    er
    1.89
     often
    1.89
     NOT
    1.84
    often
    1.83
    卑
    1.82
    POSITIVE LOGITS
    ਆ
    2.24
    жей
    2.19
     Permalink
    2.15
    ρακ
    2.15
    heastern
    2.09
    SDLCheck
    2.04
    ಲ್ಲು
    2.04
    LineEdit
    2.01
    ンダント
    1.99
     beforePath
    1.99
    Activations Density 0.141%

    No Known Activations