© 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. 228188
    Prev
    Next
    INDEX
    Explanations

    phrases starting with specific words

    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
    itelj
    0.48
    ät
    0.48
    is
    0.47
    un
    0.46
    н
    0.46
    U
    0.44
    reward
    0.44
    Bubble
    0.44
    an
    0.43
    isem
    0.43
    POSITIVE LOGITS
     scenarios
    0.56
     escenas
    0.50
     escenarios
    0.49
     arbitrage
    0.48
    '};
    0.46
     figures
    0.46
     alba
    0.46
     advis
    0.46
     industria
    0.46
     organizaciones
    0.46
    Activations Density 0.001%

    No Known Activations