© 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. 44458
    Prev
    Next
    INDEX
    Explanations

    wavelength of light

    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
    ،
    0.53
    چے
    0.51
    '،
    0.48
    سر
    0.46
     socialism
    0.46
     matrimonial
    0.45
     Netanyahu
    0.45
    纠
    0.45
     injunction
    0.44
    بر
    0.44
    POSITIVE LOGITS
     denotes
    0.50
     denoted
    0.50
     நிற
    0.48
     Mpc
    0.47
     विस्तृत
    0.47
     gripped
    0.47
    denoted
    0.46
     mostly
    0.45
     অস্থায়ী
    0.44
     whitish
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.