© 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. 21633
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    entity + descriptor

    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
    了一声
    0.46
    मै
    0.46
    ม
    0.46
     godinu
    0.45
     siquiera
    0.45
     stanu
    0.45
     skladu
    0.43
     apartamentos
    0.43
    二年
    0.42
    朓
    0.41
    POSITIVE LOGITS
     συμμε
    0.52
    will
    0.52
    oz
    0.50
    oppers
    0.50
    affinity
    0.50
     proactive
    0.49
    WILL
    0.47
     will
    0.47
    expr
    0.46
    ACTIVE
    0.45
    Activations Density 0.000%

    No Known Activations