© 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. 5894
    Prev
    Next
    INDEX
    Explanations

    sales and financial performance

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

    motivations and actions

    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
     sekar
    0.51
     neige
    0.51
     médicament
    0.46
    鳝
    0.44
     terrains
    0.44
     organismes
    0.43
    铉
    0.43
     налого
    0.43
     الاخر
    0.42
    楽器
    0.42
    POSITIVE LOGITS
     greed
    0.48
     decena
    0.46
     mostly
    0.44
     ambitious
    0.44
    貪
    0.43
     ventas
    0.41
     主要
    0.41
    three
    0.41
     seven
    0.41
     greedy
    0.41
    Activations Density 0.000%

    No Known Activations