© 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. 91695
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    estimated bill

    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
     周
    0.51
    ají
    0.48
    aysa
    0.48
     Nasr
    0.48
     භ
    0.47
     Ratch
    0.47
     perkara
    0.46
     provinsi
    0.46
     比
    0.46
     Piy
    0.46
    POSITIVE LOGITS
     coc
    0.46
    МО
    0.45
     originale
    0.44
    ★★
    0.43
     ήταν
    0.42
     aggravating
    0.41
    调节
    0.41
    榜
    0.40
    感谢
    0.40
    ল্প
    0.39
    Activations Density 0.000%

    No Known Activations