© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7636
    Prev
    Next
    INDEX
    Explanations

    words starting with h

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     році
    2.27
    aqueous
    2.13
    嶇
    2.08
    лій
    2.08
     vrem
    2.04
    岖
    2.01
    embre
    1.99
    春秋
    1.99
     crates
    1.98
     bols
    1.98
    POSITIVE LOGITS
    izontal
    2.71
    ricane
    2.46
    pertension
    2.41
    рактери
    2.36
    benzo
    2.25
    ゚
    2.22
    derabad
    2.17
    bollah
    2.16
    مش
    2.03
    scotch
    2.00
    Activations Density 0.577%

    No Known Activations