© 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. 280
    Prev
    Next
    INDEX
    Explanations

    wind followed by punctuation

    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
     bit
    0.88
     [
    0.86
     XI
    0.81
     `
    0.80
     XXX
    0.80
     averse
    0.76
     never
    0.75
     naked
    0.75
     hele
    0.74
     mild
    0.74
    POSITIVE LOGITS
    ）。
    1.57
    ],
    1.56
    》，
    1.56
    )،
    1.52
    ]).
    1.50
    %。
    1.49
    },
    1.48
    】,
    1.48
    ]，
    1.48
    ）、
    1.46
    Activations Density 0.424%

    No Known Activations