© 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. 508
    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_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
    ^{*}(\
    1.18
    _{*}(
    1.14
    ^{*}=\
    1.08
    anilide
    1.06
    ^{\#}\
    1.05
     ලබා
    1.04
    ^{-(
    1.02
    isor
    1.01
    '_{\
    1.01
    _{+}-
    1.00
    POSITIVE LOGITS
     yeah
    3.26
     Yeah
    3.08
    yeah
    3.01
    Yeah
    2.95
     yep
    2.82
     oh
    2.81
     hmm
    2.80
     Hmm
    2.74
     yes
    2.69
     wow
    2.69
    Activations Density 4.904%

    No Known Activations