© 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. 156881
    Prev
    Next
    INDEX
    Explanations

    no or nor

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

    depending on

    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
    zor
    0.50
     अक्सर
    0.49
    Z
    0.48
    Understand
    0.46
    ൻ
    0.46
    ZE
    0.44
     אז
    0.44
    क्सर
    0.42
    AYS
    0.42
     rheumatism
    0.41
    POSITIVE LOGITS
     zwölf
    0.46
     وقلنا
    0.44
    etse
    0.44
     couvert
    0.44
    ifact
    0.44
     constitu
    0.43
    woven
    0.43
     suivie
    0.43
    ':[
    0.43
    ruppen
    0.43
    Activations Density 0.005%

    No Known Activations