© 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. 7-GEMMASCOPE-2-RES-16K
    7. 236
    Prev
    Next
    INDEX
    Explanations

    in the

    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_7_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
    falt
    1.12
     heeft
    1.10
     pentru
    1.08
     більше
    1.08
    การ
    1.05
    imetric
    1.03
    игры
    1.02
    睺
    1.02
    erequisites
    1.02
     utilizzato
    1.01
    POSITIVE LOGITS
    habitants
    1.11
     spite
    1.04
     midst
    1.01
    volving
    0.99
     Southern
    0.98
     Northern
    0.95
     northern
    0.95
    spired
    0.95
     vicinity
    0.94
     depths
    0.94
    Activations Density 2.861%

    No Known Activations