© 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. 90290
    Prev
    Next
    INDEX
    Explanations

    airport

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

    Robb Stark, hull, gradients, prime

    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
     exons
    0.50
     smells
    0.49
     abbreviations
    0.49
     codons
    0.47
     apellidos
    0.47
    ####
    0.46
     penyebab
    0.46
     Hickory
    0.46
     absences
    0.46
     represents
    0.45
    POSITIVE LOGITS
    奮
    0.46
    take
    0.46
    ove
    0.45
    craft
    0.44
    że
    0.44
    سین
    0.43
     करतात
    0.42
    ov
    0.42
    expand
    0.42
    egn
    0.42
    Activations Density 0.000%

    No Known Activations