© 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. 41234
    Prev
    Next
    INDEX
    Explanations

    dropped immediately

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

    foreign scripts or specific terms

    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
     orbits
    0.52
     coûte
    0.50
     ऑर्
    0.48
     doodle
    0.47
    ^{*}+
    0.47
     nonEmpty
    0.46
     orbit
    0.46
     episcop
    0.45
     argent
    0.44
     handleChange
    0.44
    POSITIVE LOGITS
    bane
    0.43
     வருக
    0.39
    Благо
    0.39
    ur
    0.39
    building
    0.38
    bred
    0.38
     Shibata
    0.38
    Thickness
    0.37
    Җ
    0.37
    feedback
    0.36
    Activations Density 0.000%

    No Known Activations