© 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. 231779
    Prev
    Next
    INDEX
    Explanations

    organizations, community, events, needs

    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
     lessened
    0.63
    듦
    0.61
     với
    0.58
    での
    0.57
     WITH
    0.57
     needing
    0.56
     furthering
    0.53
     with
    0.51
     lessening
    0.51
    是
    0.51
    POSITIVE LOGITS
     பெரும்பாலான
    0.66
     પરંતુ
    0.57
     परंतु
    0.57
     პ
    0.55
     コ
    0.54
     झाल्यानंतर
    0.54
    brahim
    0.53
     ケ
    0.53
     ähm
    0.53
     ஹ
    0.52
    Activations Density 0.306%

    No Known Activations