© 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. 144005
    Prev
    Next
    INDEX
    Explanations

    negotiations, pans, patron

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

    Mercantilism, whatever, **Biopsy**, paraphimosis, Madmoizelle, staff, violation, slightly

    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
     tortues
    0.53
     ké
    0.52
     _;
    0.48
    Ketika
    0.48
     ပါ
    0.48
     শঙ্ক
    0.48
    ১২
    0.47
     lézards
    0.47
     після
    0.47
     consultez
    0.47
    POSITIVE LOGITS
    3
    0.55
    )
    0.48
    2
    0.47
    cial
    0.46
     Strom
    0.46
     Comparative
    0.46
    pt
    0.45
    strom
    0.45
    propyl
    0.44
    HU
    0.43
    Activations Density 0.000%

    No Known Activations