© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11947
    Prev
    Next
    INDEX
    Explanations

    the trevor project

    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_13_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
     своём
    1.53
     своё
    1.33
     моём
    1.30
     идёт
    1.29
     Allentown
    1.26
    凄い
    1.26
    Colored
    1.23
    슴
    1.23
     Flavor
    1.18
     আমায়
    1.16
    POSITIVE LOGITS
     recognising
    1.46
    authorised
    1.40
     generalised
    1.34
     recognised
    1.30
     mobilise
    1.29
     recognisable
    1.28
     relevant
    1.26
     pivotal
    1.26
     marginalised
    1.25
     globalisation
    1.24
    Activations Density 0.090%

    No Known Activations