© 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. 259
    Prev
    Next
    INDEX
    Explanations

    'd contractions

    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
     :).
    1.13
     물론
    1.12
    !!.
    1.10
    !.
    1.10
    }.
    1.05
     }.
    1.05
    ።
    1.04
     puisque
    0.99
    }^{+},
    0.99
    ۔
    0.98
    POSITIVE LOGITS
     is
    1.93
     has
    1.93
     will
    1.86
     appears
    1.84
     can
    1.75
     constitutes
    1.74
     are
    1.74
     could
    1.70
     seems
    1.69
     cannot
    1.68
    Activations Density 9.646%

    No Known Activations