© 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. 3656
    Prev
    Next
    INDEX
    Explanations

    bio, neuro, and eco applications

    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
    ına
    1.96
     CCc
    1.83
    ћин
    1.72
    OUBLE
    1.72
     број
    1.70
     doigt
    1.67
    (',',$
    1.64
    ַ
    1.64
     uš
    1.63
    лизова
    1.62
    POSITIVE LOGITS
    reset
    1.74
    hazardous
    1.66
    boosting
    1.62
    Rx
    1.62
    assay
    1.58
    Preferred
    1.54
    uximab
    1.54
    accumulation
    1.53
    transfer
    1.52
    reb
    1.51
    Activations Density 0.188%

    No Known Activations