© 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. 64093
    Prev
    Next
    INDEX
    Explanations

    lift, diamond, business, chocolate, energy, wall, human

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

    HTML tags and structure

    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
    2
    0.60
    4
    0.55
    ’
    0.55
    5
    0.53
    7
    0.53
    3
    0.52
    un
    0.51
    1
    0.51
     outfitted
    0.50
    পূর্ণ
    0.49
    POSITIVE LOGITS
     realise
    0.61
     realises
    0.60
     tumours
    0.55
     leuke
    0.54
     احمد
    0.54
    ですし
    0.53
     kullanımı
    0.53
     deje
    0.52
     vermel
    0.52
     brug
    0.52
    Activations Density 0.000%

    No Known Activations