© 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. 91802
    Prev
    Next
    INDEX
    Explanations

    profile and location details

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

    psychological states and logistical/technical setups

    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
    ata
    0.52
    award
    0.47
     ១
    0.47
    MBA
    0.46
     chết
    0.46
     laughs
    0.45
    ară
    0.45
    HW
    0.45
     десять
    0.43
    ઠી
    0.43
    POSITIVE LOGITS
     roller
    0.54
     kaleidoscope
    0.53
    ंजलि
    0.52
    ⟋
    0.47
    ാനും
    0.47
     leit
    0.47
     transactional
    0.46
     navigational
    0.46
     jangka
    0.46
     rollercoaster
    0.45
    Activations Density 0.001%

    No Known Activations