© 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. 158302
    Prev
    Next
    INDEX
    Explanations

    states of being, concepts, or attributes

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

    specific topics and their associated descriptors

    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
    aturally
    0.40
    樘
    0.38
     안정
    0.37
    objects
    0.36
    policies
    0.36
    ленность
    0.36
    opathies
    0.35
    ô
    0.35
    tam
    0.35
     อืม
    0.35
    POSITIVE LOGITS
     (!)
    0.45
    (!)
    0.40
     Investigación
    0.39
     indiquant
    0.39
     cuidadosamente
    0.38
     excitedly
    0.38
     explica
    0.37
    蓝色
    0.37
     intenta
    0.35
     artículos
    0.35
    Activations Density 0.193%

    No Known Activations