© 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. 227365
    Prev
    Next
    INDEX
    Explanations

    specific phrases and entities

    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
    т
    0.56
     impactful
    0.50
    ⇅
    0.50
     или
    0.46
    ეც
    0.45
     истори
    0.45
    ২১
    0.44
    आपके
    0.43
    rcl
    0.43
    
    0.43
    POSITIVE LOGITS
     set
    0.53
     Padova
    0.48
     ue
    0.46
    イオン
    0.45
     wykorzyst
    0.44
     squadra
    0.44
     selezione
    0.44
     作業
    0.43
     Phan
    0.43
     mor
    0.43
    Activations Density 0.000%

    No Known Activations