© 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. 70510
    Prev
    Next
    INDEX
    Explanations

    aboriginal communities, intelligence, veterans

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

    grand claims, smaller shops, root->

    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
    नु
    0.59
    في
    0.47
    之后
    0.47
    то
    0.47
    তেন
    0.47
    㩽
    0.46
    तरह
    0.46
    還要
    0.46
    ஸ்தான
    0.46
    들
    0.45
    POSITIVE LOGITS
     θέ
    0.44
     विधवा
    0.44
     bitches
    0.43
     Chees
    0.43
     သင်
    0.43
     Vogue
    0.42
     cra
    0.42
     Butch
    0.42
     Mia
    0.42
     Bookmark
    0.42
    Activations Density 0.000%

    No Known Activations