© 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. 174146
    Prev
    Next
    INDEX
    Explanations

    name endings ending in -ov or -ev

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

    v followed by numbers

    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
     età
    0.55
    ون
    0.50
    रम
    0.50
     ouverture
    0.50
     alumina
    0.50
     utilizzando
    0.48
     a
    0.48
    levision
    0.48
     gewoon
    0.48
    し
    0.48
    POSITIVE LOGITS
    v
    0.64
    рачи
    0.56
    ный
    0.55
     дальнейшем
    0.51
     авгу
    0.50
     дальше
    0.50
    нимание
    0.50
    icioso
    0.50
     самом
    0.49
    τεί
    0.48
    Activations Density 0.276%

    No Known Activations