© 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. 238814
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or combinations

    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
    mult
    0.50
    a
    0.47
    updater
    0.46
    klar
    0.44
    tournament
    0.43
    emene
    0.43
     போட்டிய
    0.43
    alim
    0.42
    informat
    0.42
     सीजीएल
    0.42
    POSITIVE LOGITS
    ется
    0.45
     ("",
    0.44
    .
    0.43
    扫
    0.41
     symptomatic
    0.41
     astronauts
    0.40
     ectopic
    0.40
     urinary
    0.40
    ΄
    0.40
     weaning
    0.40
    Activations Density 0.000%

    No Known Activations