© 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. 134632
    Prev
    Next
    INDEX
    Explanations

    project, maintenance, site

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

    existentialism and created meaning

    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
    적인
    0.52
    리로
    0.51
    징
    0.41
     jungle
    0.40
     dominance
    0.40
    럴
    0.40
     modes
    0.39
     친
    0.39
     batches
    0.39
     customised
    0.39
    POSITIVE LOGITS
    butoxy
    0.59
    проек
    0.58
     comentário
    0.54
    querda
    0.53
    did
    0.53
    éa
    0.52
    projection
    0.52
     avenida
    0.51
     अंग्रे
    0.50
     Obrig
    0.49
    Activations Density 0.000%

    No Known Activations