© 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. 209093
    Prev
    Next
    INDEX
    Explanations

    Defender AV

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

    foreign characters and landmarks

    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
     de
    0.52
     Lö
    0.50
     ö
    0.48
     Liu
    0.47
     hated
    0.47
    elle
    0.46
    ution
    0.46
    usion
    0.46
    lation
    0.46
    ated
    0.45
    POSITIVE LOGITS
    כר
    0.55
    สวัสดี
    0.48
    齙
    0.48
    ει
    0.46
    θεί
    0.46
    дис
    0.46
    이크
    0.46
     להיות
    0.46
    шель
    0.46
    다
    0.46
    Activations Density 0.000%

    No Known Activations