© 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. 89072
    Prev
    Next
    INDEX
    Explanations

    introduces relating degrees

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

    common opinions and historical patterns

    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
    ◹
    0.50
    рю
    0.45
    ത്തിലേക്ക്
    0.45
    рядок
    0.44
    ិត្ត
    0.44
    лександр
    0.44
    ermanfaat
    0.43
    😏
    0.43
     действий
    0.43
    ્ટ
    0.42
    POSITIVE LOGITS
     entsprechenden
    0.54
     bezeichnet
    0.51
     relate
    0.47
     empirically
    0.46
     manje
    0.46
     فول
    0.45
     jeweils
    0.45
     weniger
    0.45
     ডিগ্রি
    0.45
     CpG
    0.44
    Activations Density 0.001%

    No Known Activations