© 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. 233402
    Prev
    Next
    INDEX
    Explanations

    certified mail, booked five

    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
    饮
    0.45
     Elig
    0.43
    ቃል
    0.43
    喜爱
    0.43
    尤其是
    0.42
     hydrol
    0.41
     lão
    0.40
    힝
    0.40
     আব্দ
    0.40
    无线
    0.40
    POSITIVE LOGITS
    ew
    0.47
    odus
    0.47
    osters
    0.47
    otest
    0.47
    ies
    0.46
    okines
    0.46
    ost
    0.45
    ude
    0.44
    eston
    0.43
    ensive
    0.43
    Activations Density 0.002%

    No Known Activations