© 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. 9157
    Prev
    Next
    INDEX
    Explanations

    verbs followed by punctuation or qualifiers

    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
     сон
    1.17
    קור
    1.16
     كيفية
    1.16
     Treatise
    1.14
     余
    1.13
     вся
    1.11
    晞
    1.11
     높은
    1.09
     خصوص
    1.09
     мере
    1.09
    POSITIVE LOGITS
    oprop
    1.56
    oflav
    1.33
    aggressive
    1.30
    propion
    1.28
    ipak
    1.25
    marin
    1.24
    flav
    1.24
    imetre
    1.24
    ikaze
    1.24
    arab
    1.21
    Activations Density 0.000%

    No Known Activations