© 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. 138401
    Prev
    Next
    INDEX
    Explanations

    selling house and appearance

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

    makes something faster or harder

    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
     proposals
    0.48
     proposing
    0.47
     miscellaneous
    0.46
     at
    0.46
     comprehensive
    0.46
     proposed
    0.45
    [
    0.44
     in
    0.44
    LESS
    0.44
    '
    0.44
    POSITIVE LOGITS
     biskup
    0.62
     bolje
    0.59
     जाणून
    0.56
    эф
    0.54
     janu
    0.54
    сив
    0.52
    вим
    0.50
     глаз
    0.50
     Luật
    0.49
    спе
    0.48
    Activations Density 0.000%

    No Known Activations