© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78039
    Prev
    Next
    INDEX
    Explanations

    phone app requirements

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

    hand lettering, SIM card, keywords

    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
    Negative Logits
     Gibson
    0.54
    കളിൽ
    0.54
     Erin
    0.53
     Jefferson
    0.52
     Gregory
    0.52
     St
    0.52
    ně
    0.52
     Faith
    0.52
    㖣
    0.51
     McNamara
    0.50
    POSITIVE LOGITS
     ancor
    0.51
     pels
    0.50
    0
    0.47
    inputs
    0.47
    四川
    0.46
    permit
    0.46
    ໂດຍ
    0.45
    hrs
    0.45
    股
    0.44
    马来
    0.44
    Activations Density 0.001%

    No Known Activations