© 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. 34936
    Prev
    Next
    INDEX
    Explanations

    true cold, true classics

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

    certain conditions or limitations

    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
    мот
    0.49
    粈
    0.48
    棪
    0.48
    че
    0.47
     Creature
    0.47
     Literacy
    0.46
    咤
    0.46
    ர்ச்சி
    0.46
     Predator
    0.46
     Light
    0.45
    POSITIVE LOGITS
    0.48
     embassies
    0.47
     wineries
    0.46
     bridesmaid
    0.46
     of
    0.46
     patente
    0.45
     insurgents
    0.44
     measurements
    0.43
     wygląd
    0.43
     enthalpies
    0.43
    Activations Density 0.000%

    No Known Activations