© 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. 39835
    Prev
    Next
    INDEX
    Explanations

    technical specifications or types

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

    shape, impact, rarity, resolution

    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
     فاس
    0.53
    ية
    0.50
    nummer
    0.49
     alcal
    0.47
    nitř
    0.46
     zieht
    0.46
    nis
    0.45
     œ
    0.45
    IT
    0.45
    ized
    0.44
    POSITIVE LOGITS
     CORP
    0.51
     Subsidi
    0.49
    क्राइब
    0.48
     Subsidiary
    0.46
     Magenta
    0.43
     PLAT
    0.42
     TRAINING
    0.40
     Kellogg
    0.40
    ]*
    0.38
     περισσότε
    0.38
    Activations Density 0.000%

    No Known Activations