© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 1382
    Prev
    Next
    INDEX
    Explanations

    emotions and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
    and
    1.04
     и
    1.00
     and
    0.99
    และ
    0.96
    ut
    0.93
    And
    0.92
     và
    0.88
    :
    0.88
    '
    0.87
     และ
    0.85
    POSITIVE LOGITS
     whatnot
    1.59
     motivations
    1.28
     각종
    1.24
     deterioration
    1.20
     관련된
    1.19
     logistical
    1.19
     miscellaneous
    1.17
     explanations
    1.17
     distractions
    1.17
     inferences
    1.16
    Activations Density 1.841%

    No Known Activations