© 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. 183956
    Prev
    Next
    INDEX
    Explanations

    trusted by

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

    phrases with conjunctions and app components

    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
     ascribed
    0.48
    귓
    0.43
     grossly
    0.43
     demonstrable
    0.42
     Encyclopædia
    0.42
     بیس
    0.42
    が無い
    0.42
    掀
    0.42
    کریاں
    0.41
     smothered
    0.41
    POSITIVE LOGITS
    ina
    0.50
     you
    0.49
    Text
    0.49
    als
    0.47
    R
    0.47
    INA
    0.47
     sodass
    0.47
    School
    0.46
    River
    0.46
    ena
    0.46
    Activations Density 0.001%

    No Known Activations