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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 108
    Prev
    Next
    INDEX
    Explanations

    verb conjugations and noun suffixes

    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
    OUGH
    0.69
    ALLY
    0.68
     الان
    0.67
     والان
    0.66
     sickle
    0.65
    แค
    0.65
    𝐤
    0.64
    LLOW
    0.64
     EVERY
    0.63
    OLY
    0.63
    POSITIVE LOGITS
    ación
    1.69
    adura
    1.54
    amento
    1.52
    és
    1.50
    ante
    1.50
    ió
    1.49
    ando
    1.48
    ado
    1.48
    ó
    1.47
    ificación
    1.47
    Activations Density 0.500%

    No Known Activations