© 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. 13-GEMMASCOPE-2-RES-16K
    7. 977
    Prev
    Next
    INDEX
    Explanations

    Privacy and confidentiality

    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
     persone
    1.24
     produkty
    1.14
    䒠
    1.14
     insanların
    1.12
     ETFs
    1.06
    龶
    1.02
    珬
    1.01
    畽
    1.01
     संस्था
    1.00
    䅐
    0.99
    POSITIVE LOGITS
     midway
    1.16
     penultimate
    1.14
     fullback
    1.08
     Larkin
    1.07
     vacated
    1.06
    arrière
    1.05
     seventeenth
    1.04
     stabbed
    1.04
     halftime
    1.04
    twice
    1.03
    Activations Density 0.495%

    No Known Activations