© 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. 178737
    Prev
    Next
    INDEX
    Explanations

    lists of entities and actions

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

    keywords and their following context

    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
    டையே
    0.49
    ंट
    0.46
    arette
    0.45
    ково
    0.45
    ко
    0.45
    缡
    0.43
    셸
    0.43
     உள்ளன
    0.42
    ிட்டு
    0.41
    áticamente
    0.41
    POSITIVE LOGITS
     idempot
    0.53
     stipend
    0.51
     G
    0.48
     સર
    0.48
     Hold
    0.47
     í
    0.46
    0.45
     জিৎ
    0.45
     Ayat
    0.45
     Id
    0.44
    Activations Density 0.001%

    No Known Activations