© 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. 22-GEMMASCOPE-2-RES-16K
    7. 540
    Prev
    Next
    INDEX
    Explanations

    CFPB, variables, currency

    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_22_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
     predetermined
    0.84
     demon
    0.83
     nesses
    0.79
     perf
    0.77
    უდ
    0.77
    <unused1240>
    0.76
    𝚔
    0.76
    <unused912>
    0.75
     regenerative
    0.75
     eren
    0.74
    POSITIVE LOGITS
     C
    1.14
     P
    1.10
     S
    1.10
     D
    1.09
    C
    1.08
     R
    1.08
     F
    1.07
    mathcal
    1.07
     Р
    1.05
    С
    1.05
    Activations Density 2.895%

    No Known Activations