© 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. 22979
    Prev
    Next
    INDEX
    Explanations

    What does or are

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

    what does questions

    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
     theorem
    0.45
    THEOREM
    0.43
     அறிமுக
    0.41
    windowFixedWidth
    0.39
    theorem
    0.39
    नोई
    0.38
    ஸ்த
    0.38
    ϑ
    0.38
     cursory
    0.38
    ಲಾಯಿತು
    0.38
    POSITIVE LOGITS
     Cities
    0.48
    masters
    0.42
     you
    0.42
     ás
    0.41
     Masters
    0.41
    akot
    0.41
     sabot
    0.40
     Tires
    0.40
     Settings
    0.40
     Workplace
    0.40
    Activations Density 0.002%

    No Known Activations