© 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. 111629
    Prev
    Next
    INDEX
    Explanations

    listing and combining ideas

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

    access, file, list, subscription, or

    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
     қ
    0.41
    之後
    0.39
     등
    0.38
     вр
    0.38
    í
    0.36
    以後
    0.36
     люби
    0.35
    美人
    0.35
     след
    0.34
    ía
    0.34
    POSITIVE LOGITS
     sekaligus
    0.50
     ataupun
    0.50
     maupun
    0.45
    及び
    0.44
     illetve
    0.42
    暨
    0.41
     bzw
    0.40
    چل
    0.40
     以及
    0.39
     oppure
    0.38
    Activations Density 0.133%

    No Known Activations