© 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. 156238
    Prev
    Next
    INDEX
    Explanations

    access to

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

    economics and science

    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
     Creed
    0.47
    说话
    0.46
    瓠
    0.46
    끼
    0.45
    狍
    0.45
     Heard
    0.44
    溱
    0.44
    蝴
    0.43
     Cria
    0.42
    娇
    0.42
    POSITIVE LOGITS
     módulos
    0.53
     wró
    0.52
     realise
    0.51
     lipids
    0.49
     realising
    0.49
     hadrons
    0.48
     operador
    0.47
     nucleons
    0.47
     nucleotides
    0.47
     frutas
    0.47
    Activations Density 0.000%

    No Known Activations