© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5163
    Prev
    Next
    INDEX
    Explanations

    ISBNs and numerical sequences

    np_acts-logits-general · gemini-2.5-flash-lite

    providing information and education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    S
    0.62
    G
    0.58
     that
    0.57
     (
    0.53
     ८
    0.52
    M
    0.52
    し
    0.52
     N
    0.51
     S
    0.51
    tiene
    0.49
    POSITIVE LOGITS
    城乡
    0.52
     grizz
    0.51
    一颗
    0.50
    పథ
    0.49
    రణ
    0.48
    ීර
    0.48
     témoign
    0.46
    ~.,
    0.45
     testAvg
    0.45
     tempHeader
    0.44
    Activations Density 0.000%

    No Known Activations