© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7117
    Prev
    Next
    INDEX
    Explanations

    what is making you feel this way

    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
    ;
    2.71
    ؛
    2.40
    ,—
    2.39
    ,
    2.37
    —
    2.33
    ;,
    2.29
     —
    2.25
    ,*
    2.16
     --
    2.13
    *,
    2.06
    POSITIVE LOGITS
     \%)$.
    1.65
    })$.
    1.60
    '].
    1.59
     %).
    1.55
    }]$.
    1.53
    .).
    1.50
     "").
    1.48
     }}$.
    1.48
    /).
    1.46
    "].
    1.46
    Activations Density 0.563%

    No Known Activations