© 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. 49172
    Prev
    Next
    INDEX
    Explanations

    fake wood or wooden

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

    ethics, carbs, knows, steps

    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
    н
    0.49
    In
    0.44
    日的
    0.44
    प्र
    0.43
    Handsome
    0.43
    ்க
    0.42
    }=(\
    0.42
    راس
    0.42
    end
    0.42
    Products
    0.42
    POSITIVE LOGITS
    rą
    0.51
     FRANCE
    0.50
     юби
    0.49
     EBIT
    0.49
     QE
    0.49
    🍮
    0.49
     やっぱり
    0.48
     mesin
    0.48
     proximal
    0.47
     queuing
    0.47
    Activations Density 0.000%

    No Known Activations