© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1492
    Prev
    Next
    INDEX
    Explanations

    introduces categorized options

    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_13_width_65k_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
     ….
    0.84
     …
    0.80
     solidly
    0.78
     solid
    0.76
    <0xA0>
    0.74
     fingern
    0.73
     legitimately
    0.72
     above
    0.72
     .
    0.70
     moderately
    0.69
    POSITIVE LOGITS
     possui
    1.71
     güçlü
    1.69
     özel
    1.64
     Terbaik
    1.64
     terbaru
    1.63
     satış
    1.58
     güzel
    1.54
     aseguró
    1.54
     araç
    1.53
     Terbaru
    1.53
    Activations Density 3.435%

    No Known Activations