© 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. 12514
    Prev
    Next
    INDEX
    Explanations

    million, student, meet specific

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

    Consistent Communication / Current Standard

    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
     குளிர்
    0.45
    𝙥
    0.45
    imagenes
    0.44
    adjustable
    0.43
    ிரிய
    0.43
    ការព
    0.43
    ದ್ದರಿಂದ
    0.43
    istungen
    0.42
     శరీర
    0.41
    僵
    0.41
    POSITIVE LOGITS
     (“
    0.49
     alias
    0.48
     (
    0.47
    ⇑
    0.47
     Wine
    0.45
     “
    0.44
     taps
    0.43
    ,
    0.43
     aka
    0.43
     Sats
    0.43
    Activations Density 0.000%

    No Known Activations