© 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. 125707
    Prev
    Next
    INDEX
    Explanations

    job position requirements

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

    job position at

    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
    q
    0.45
    "
    0.44
     module
    0.42
    module
    0.42
    stack
    0.41
     Ju
    0.41
    OU
    0.40
    Kü
    0.40
    uti
    0.40
    output
    0.39
    POSITIVE LOGITS
     nécess
    0.53
    퓰
    0.51
    зина
    0.50
    뮬
    0.48
     philanthropic
    0.47
     fermeture
    0.47
    meld
    0.46
     publicaciones
    0.46
    דו
    0.46
     élections
    0.46
    Activations Density 0.034%

    No Known Activations