© 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. 17-GEMMASCOPE-2-RES-16K
    7. 207
    Prev
    Next
    INDEX
    Explanations

    space and shapes

    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_17_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
     Rehab
    1.23
     Verbal
    1.23
     biber
    1.18
     Cots
    1.17
     CBT
    1.16
     竹
    1.13
     الوز
    1.12
     verbal
    1.10
     CWE
    1.10
    茯
    1.10
    POSITIVE LOGITS
     planets
    3.71
     planet
    3.52
     astronomers
    3.33
     asteroids
    3.30
     asteroid
    3.28
     spacecraft
    3.25
     Planet
    3.22
     Planets
    3.22
     planetary
    3.20
     planeta
    3.13
    Activations Density 2.476%

    No Known Activations