© 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. 13-GEMMASCOPE-2-RES-16K
    7. 4446
    Prev
    Next
    INDEX
    Explanations

    explaining why it's good

    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
     でしょう
    2.31
     ござい
    2.13
     いたし
    2.03
     ^{\
    2.01
     いう
    1.98
     _{(
    1.98
     たり
    1.96
     』
    1.93
     ју
    1.93
     なく
    1.91
    POSITIVE LOGITS
    :
    4.88
    ?:
    3.47
    ：
    3.43
    :-
    3.07
    +:
    2.99
    :“
    2.95
    ):
    2.92
    .:
    2.84
    !:
    2.82
    :*
    2.82
    Activations Density 0.322%

    No Known Activations