© 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. 176042
    Prev
    Next
    INDEX
    Explanations

    America, Appalachian Trail, verbal communication

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

    when your, often not

    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
    アク
    0.45
    voorbeeld
    0.44
    다음
    0.43
     આજ
    0.43
    ਨ
    0.43
     for
    0.42
    सन
    0.42
    KA
    0.42
    സ്സ
    0.41
     സംഭവ
    0.41
    POSITIVE LOGITS
    ্ডিং
    0.48
     клави
    0.47
     perce
    0.45
    тина
    0.45
     Hera
    0.45
     Perce
    0.45
    тли
    0.45
     Marcin
    0.45
    <unused2200>
    0.44
     Qin
    0.43
    Activations Density 0.000%

    No Known Activations