© 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. 524
    Prev
    Next
    INDEX
    Explanations

    instructional or descriptive verbs

    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
     notificación
    1.14
    ࢮ
    1.13
    𒁍
    1.12
    꾻
    1.10
    䳕
    1.10
    𒆳
    1.10
    뿯
    1.10
    𒀝
    1.09
    𒆷
    1.07
    𒆪
    1.06
    POSITIVE LOGITS
     high
    0.85
     freely
    0.85
     a
    0.84
     anywhere
    0.82
     up
    0.82
     any
    0.80
     it
    0.79
     your
    0.79
     very
    0.79
     this
    0.77
    Activations Density 7.107%

    No Known Activations