© 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. 66373
    Prev
    Next
    INDEX
    Explanations

    from to

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

    not nervous, patient, revenue, shi

    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
    Friday
    0.46
    ंग्रेस
    0.46
     STARS
    0.45
    𝗧
    0.43
    ກ
    0.43
    𝗷
    0.43
    伊朗
    0.42
    修改
    0.42
     शुरुआती
    0.42
    京东
    0.42
    POSITIVE LOGITS
     belang
    0.44
     neurotic
    0.44
     erat
    0.43
     bangun
    0.42
     pote
    0.41
     poten
    0.41
     wych
    0.41
     transforme
    0.41
     veldig
    0.41
     hängt
    0.41
    Activations Density 0.000%

    No Known Activations