© 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. 257926
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     sadistic
    0.51
     దో
    0.48
    </h4>
    0.45
    iction
    0.44
    ία
    0.44
    ick
    0.43
     घेऊ
    0.43
     spirit
    0.43
     נ
    0.42
     agonists
    0.42
    POSITIVE LOGITS
    atsi
    0.54
     Perché
    0.53
    ANSI
    0.52
    arlama
    0.51
    anske
    0.50
     BONDS
    0.49
    цкі
    0.49
     ریلی
    0.49
     Infine
    0.49
    arları
    0.49
    Activations Density 0.000%

    No Known Activations