© 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. 189161
    Prev
    Next
    INDEX
    Explanations

    flat and smooth surfaces

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

    smooth skin

    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
    is
    0.68
     et
    0.61
     }
    0.57
     atmosfer
    0.55
    atmosphere
    0.54
     atmosfera
    0.54
    odule
    0.53
     atmosphere
    0.51
    i
    0.51
    l
    0.51
    POSITIVE LOGITS
    平
    1.17
     FLAT
    1.15
     flatness
    1.13
     flat
    1.12
    flat
    1.06
     smoother
    1.05
    Flat
    1.04
    smooth
    1.02
     平
    1.02
     smooth
    1.01
    Activations Density 0.278%

    No Known Activations