© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30604
    Prev
    Next
    INDEX
    Explanations

    URLs and special characters

    np_acts-logits-general · gemini-2.5-flash-lite

    emojis and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     retweet
    0.52
     🙌
    0.47
     👇
    0.46
    ️⃣
    0.46
    ⃣
    0.44
     http
    0.43
    nél
    0.43
     díky
    0.42
     unsurprisingly
    0.42
    ❗
    0.41
    POSITIVE LOGITS
    ,—
    0.44
    ――
    0.42
     isa
    0.42
    ZQ
    0.41
    －－
    0.40
    ;',
    0.40
    」，
    0.39
    筞
    0.39
    ——
    0.38
    Side
    0.38
    Activations Density 0.002%

    No Known Activations