© 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. 159517
    Prev
    Next
    INDEX
    Explanations

    ordering or defining terms

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

    Check Microsoft compatibility

    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
     منصور
    0.47
     retraction
    0.47
     retract
    0.46
     positron
    0.46
     رس
    0.46
     retreat
    0.45
     ¿
    0.44
     positivity
    0.44
     Kira
    0.43
    |-
    0.43
    POSITIVE LOGITS
    ጀት
    0.48
    uradaki
    0.47
     escalas
    0.47
    ಬ್ಬಿಣ
    0.46
    ώσει
    0.46
    hasNext
    0.46
    োনাম
    0.45
     encapsulates
    0.45
    qz
    0.45
    snapshots
    0.45
    Activations Density 0.004%

    No Known Activations