© 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. 60320
    Prev
    Next
    INDEX
    Explanations

    We 3

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

    transitional phrases and context connectors

    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
     Αγ
    0.51
    𝒮
    0.46
     Εκ
    0.43
     Α
    0.42
     LEC
    0.42
     AIDS
    0.41
     ビタミン
    0.41
     وأن
    0.41
    𝔸
    0.41
     Νο
    0.41
    POSITIVE LOGITS
    epend
    0.51
     fires
    0.43
    anesh
    0.43
     pipes
    0.43
    的速度
    0.42
    
    0.41
     commutes
    0.41
     journeys
    0.41
    aving
    0.40
    팜
    0.40
    Activations Density 0.000%

    No Known Activations