© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 104848
    Prev
    Next
    INDEX
    Explanations

    related to media and activities

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

    conditional phrases before clauses

    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
     Duration
    0.49
     Refresh
    0.46
     Forty
    0.45
    Spec
    0.45
     Fifty
    0.44
     Fleece
    0.44
     Actually
    0.43
    0
    0.43
     Relax
    0.43
     Thirty
    0.42
    POSITIVE LOGITS
     heterozygous
    0.48
     принадлежит
    0.47
     υπάρχει
    0.45
    ocop
    0.44
    accarat
    0.44
     আছে
    0.44
    badlogic
    0.44
     cbind
    0.44
     homozygous
    0.43
     isotopic
    0.43
    Activations Density 0.000%

    No Known Activations