© 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. 161142
    Prev
    Next
    INDEX
    Explanations

    foreign language legal phrases

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

    eventuali infezioni

    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
    hang
    0.44
    或者
    0.42
    ng
    0.41
    ranial
    0.41
    up
    0.41
    book
    0.41
    6
    0.41
    häng
    0.41
     Republik
    0.41
    7
    0.41
    POSITIVE LOGITS
     contaminant
    0.49
    いを
    0.48
     получили
    0.48
     deleterious
    0.46
     вико
    0.45
    讒
    0.44
     знали
    0.44
     infraction
    0.44
     внесен
    0.44
     потер
    0.43
    Activations Density 0.001%

    No Known Activations