© 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. 303
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    o
    1.64
    ́
    1.62
    er
    1.53
    Ã
    1.44
     From
    1.41
    j
    1.41
    yes
    1.40
    has
    1.38
    oooooooo
    1.35
    oj
    1.33
    POSITIVE LOGITS
    깥
    1.73
    wpilib
    1.66
    டியோ
    1.61
    =('
    1.59
     yaptık
    1.57
    ᴋ
    1.56
    ᴇ
    1.55
    sframe
    1.55
     hurtful
    1.52
     disruptive
    1.52
    Activations Density 8.772%

    No Known Activations