© 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. 258576
    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
    üste
    0.50
    igste
    0.47
     Avoiding
    0.46
    érist
    0.46
     ਨਹੀਂ
    0.46
    瞭
    0.44
     Ultrasonic
    0.43
    ēi
    0.43
    ⎙
    0.42
    émie
    0.42
    POSITIVE LOGITS
    ᱐
    0.53
    ्म
    0.48
    bat
    0.46
     سير
    0.45
    љ
    0.44
    цию
    0.43
    filtered
    0.43
     plethora
    0.43
    Chord
    0.43
    يات
    0.43
    Activations Density 0.001%

    No Known Activations