© 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. 4429
    Prev
    Next
    INDEX
    Explanations

    emojis, alignment, DOM, vaccines

    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
     another
    0.52
     Py
    0.48
    aria
    0.47
     that
    0.47
    rite
    0.47
    e
    0.46
     S
    0.46
    man
    0.45
     K
    0.45
     P
    0.44
    POSITIVE LOGITS
     changements
    0.50
     comportamenti
    0.50
     denke
    0.48
     سیاست
    0.47
     शुर
    0.47
     douleurs
    0.46
    chodzi
    0.46
     situazioni
    0.46
     आत्मविश्वास
    0.46
     गायब
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.