© 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. 12780
    Prev
    Next
    INDEX
    Explanations

    factorial function

    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
    ﮧ
    2.73
    ه
    2.58
    ূনতম
    2.54
     "./
    2.53
    e
    2.53
    floxacin
    2.51
    izontal
    2.51
    ុម
    2.49
    o
    2.44
    öst
    2.43
    POSITIVE LOGITS
    elaide
    3.64
    fixed
    3.17
     hoc
    3.16
     fixed
    3.12
     Fixed
    3.07
    Fixed
    3.02
    ൃശ
    2.59
     zob
    2.53
     tert
    2.49
    ことが多い
    2.41
    Activations Density 0.049%

    No Known Activations