© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 6999
    Prev
    Next
    INDEX
    Explanations

    . followed by sentence start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    0.47
     этих
    0.45
    =
    0.45
    name
    0.42
     name
    0.41
    -
    0.41
    _
    0.40
     directly
    0.39
    0.39
     этом
    0.39
    POSITIVE LOGITS
     esimerkiksi
    0.57
     Nonetheless
    0.56
     Nevertheless
    0.56
     Certaines
    0.54
     Tuttavia
    0.49
     Moreover
    0.49
     Exceptions
    0.49
     এমনকি
    0.49
     SMEs
    0.48
     Zudem
    0.48
    Activations Density 0.003%

    No Known Activations