© 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. 9219
    Prev
    Next
    INDEX
    Explanations

    if/toggle on/off

    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
     somehow
    1.51
     sentient
    1.48
     Possibly
    1.44
     possibly
    1.44
     Whenever
    1.43
    cloudinary
    1.41
     Maybe
    1.41
    ྩ
    1.41
     microcos
    1.40
     exemplify
    1.39
    POSITIVE LOGITS
    Simon
    1.22
    Pakistan
    1.16
    VK
    1.15
    UAE
    1.14
    India
    1.14
    GE
    1.14
    USA
    1.11
    EC
    1.10
    ZB
    1.09
    BO
    1.08
    Activations Density 0.000%

    No Known Activations