© 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. 88348
    Prev
    Next
    INDEX
    Explanations

    immigration visa petition

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

    exotic sound, specific company details

    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
     sporadic
    0.46
     groupings
    0.44
     shik
    0.44
     익
    0.43
     affidavits
    0.43
     impeachment
    0.43
     stresses
    0.42
     committees
    0.42
    चणी
    0.42
    ເຕ
    0.42
    POSITIVE LOGITS
    ’
    0.53
    ,’
    0.49
    w
    0.47
    itating
    0.44
    ’’
    0.44
     distro
    0.43
     mús
    0.43
    mack
    0.43
     что
    0.42
     тури
    0.42
    Activations Density 0.001%

    No Known Activations