© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8146
    Prev
    Next
    INDEX
    Explanations

    Spanish verbs imperative/subjunctive

    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_22_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
     трёх
    1.93
     нём
    1.87
     ș
    1.82
     тяжё
    1.79
     ещё
    1.78
     kalo
    1.77
     учё
    1.77
     colorful
    1.75
    вёр
    1.73
     определён
    1.71
    POSITIVE LOGITS
    Whilst
    2.28
     Whilst
    2.12
     recognising
    2.07
     recognised
    2.02
     recognises
    2.02
     (£
    1.84
     utilising
    1.82
     utilises
    1.78
     recognise
    1.78
     recognisable
    1.72
    Activations Density 0.480%

    No Known Activations