© 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. 181702
    Prev
    Next
    INDEX
    Explanations

    commercial products and services

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

    cost and size

    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
    пону
    0.47
     számos
    0.46
     biên
    0.45
    hunter
    0.44
    鐨
    0.44
    呚
    0.43
    算出
    0.43
    许多
    0.42
    給我
    0.42
    多家
    0.42
    POSITIVE LOGITS
    ando
    0.51
     Protective
    0.51
     overburden
    0.47
     І
    0.46
     counterpart
    0.46
     billions
    0.45
     erf
    0.45
     Evangelical
    0.44
     Vs
    0.44
    ،
    0.44
    Activations Density 0.000%

    No Known Activations