© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3745
    Prev
    Next
    INDEX
    Explanations

    modal verbs and pronouns

    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_15_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
    schemaLocation
    1.09
     iterated
    1.08
    реди
    1.02
     verso
    0.99
    슷
    0.99
    transmitter
    0.98
    رحب
    0.97
     جنس
    0.96
    folded
    0.96
    ](../
    0.95
    POSITIVE LOGITS
     man
    2.42
    私たちは
    2.10
     우리는
    2.08
     ich
    2.05
     оно
    2.01
     we
    1.99
    they
    1.96
    there
    1.94
     they
    1.93
     вона
    1.88
    Activations Density 0.009%

    No Known Activations