© 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. 20032
    Prev
    Next
    INDEX
    Explanations

    Phantom **Thread**

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

    phantom trades or not destruction

    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
    avy
    0.47
     Anxiety
    0.43
     অজানা
    0.43
    lequin
    0.43
    𝙔
    0.42
     minuto
    0.41
     blockers
    0.41
    ;
    0.41
    awks
    0.40
    াকে
    0.40
    POSITIVE LOGITS
     questões
    0.47
    年月日
    0.46
     beschäft
    0.45
     certify
    0.45
    ották
    0.45
     التمث
    0.44
    Tt
    0.43
    汉
    0.43
     पाण्याच्या
    0.42
     coursework
    0.42
    Activations Density 0.000%

    No Known Activations