© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8875
    Prev
    Next
    INDEX
    Explanations

    her followed by possessive or action

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

    introducing specific types

    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_40_width_16k_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
    -
    0.60
    Y
    0.46
    _
    0.45
    F
    0.44
    ти
    0.43
     Ä
    0.42
    /
    0.41
    <0x0D>
    0.41
     XOR
    0.40
     Peres
    0.40
    POSITIVE LOGITS
     ठिकाणी
    0.67
    家伙
    0.67
     konuda
    0.66
     випадку
    0.66
     negócio
    0.64
     জিনিসের
    0.63
     esetben
    0.62
     ነገር
    0.61
     কারণেই
    0.61
     мнению
    0.59
    Activations Density 0.508%

    No Known Activations