© 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. 252660
    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
     aspirants
    0.55
     âg
    0.55
    ۇر
    0.52
    candidates
    0.51
    ])
    0.50
     děti
    0.49
    ')
    0.48
    });
    0.48
    andidates
    0.48
     namani
    0.48
    POSITIVE LOGITS
    ني
    0.53
    一番
    0.46
    לי
    0.46
    mailer
    0.45
    ໄປ
    0.44
     soaking
    0.44
    ô
    0.44
    诡
    0.43
     perfe
    0.43
    憸
    0.43
    Activations Density 0.000%

    No Known Activations