© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 49695
    Prev
    Next
    INDEX
    Explanations

    morningstaple, bought, morelevel

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

    ew drug

    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
    ∩
    0.19
    
    0.18
    >,
    0.18
    ▷
    0.18
     hydroxide
    0.18
     airfoil
    0.18
    骼
    0.18
     proportionality
    0.18
     三
    0.17
    ustomer
    0.17
    POSITIVE LOGITS
    zinha
    0.28
    та
    0.26
    zinho
    0.26
    an
    0.25
    yout
    0.24
    檤
    0.24
    זה
    0.24
    е
    0.24
    वश
    0.23
    funktion
    0.23
    Activations Density 0.042%

    No Known Activations