© 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. 128644
    Prev
    Next
    INDEX
    Explanations

    sinister red, food ingredients, discounts, restricted access

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

    Practice and examples

    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
     गह
    0.47
     diversifying
    0.45
     apologized
    0.44
    ᐟ
    0.42
     ရှ
    0.42
     repayments
    0.41
    ixed
    0.41
    mercial
    0.40
     outings
    0.39
    orer
    0.39
    POSITIVE LOGITS
     rifless
    0.57
    ία
    0.52
     Aéroport
    0.49
    ρα
    0.49
     macht
    0.49
     réception
    0.49
    ţ
    0.48
     mă
    0.47
    kunft
    0.47
     Vittorio
    0.47
    Activations Density 0.002%

    No Known Activations