© 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. 105782
    Prev
    Next
    INDEX
    Explanations

    variety of terms and languages

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

    variety and missed opportunities

    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
    ล็
    0.53
    シェ
    0.49
    Стра
    0.45
    ρου
    0.43
    чества
    0.43
    Mutex
    0.42
    रु
    0.41
    ャ
    0.41
    Armor
    0.41
    アフ
    0.41
    POSITIVE LOGITS
     variedade
    0.57
     verschiedenen
    0.50
     variedad
    0.47
    Variety
    0.47
     variety
    0.45
     kinderen
    0.45
     legis
    0.45
    variety
    0.45
     milyon
    0.44
     bambini
    0.44
    Activations Density 0.001%

    No Known Activations