© 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. 4679
    Prev
    Next
    INDEX
    Explanations

    installing libraries and software

    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
     nossa
    2.30
    !!
    2.27
     nosso
    2.22
    !
    2.18
     disini
    2.15
    !!!
    2.15
     nostra
    2.13
     nossas
    2.08
     /
    1.91
     hereby
    1.89
    POSITIVE LOGITS
     staffers
    3.63
     lawmakers
    3.44
     protesters
    3.43
     overhauled
    3.22
     dozens
    3.22
     Reuters
    3.19
     Britons
    3.15
     eight
    3.11
     aides
    3.10
     nine
    3.09
    Activations Density 0.769%

    No Known Activations