© 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. 10286
    Prev
    Next
    INDEX
    Explanations

    numbers, lists, and sequential steps

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

    rely on, need to, vulnerable to, adhere to

    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
     düşük
    0.51
     पर्यटक
    0.51
    炡
    0.50
    ப்பழ
    0.49
     seafront
    0.48
     ట
    0.48
     தொழில்நுட்ப
    0.47
     ছুই
    0.47
     Sì
    0.47
    лятор
    0.47
    POSITIVE LOGITS
    ue
    0.46
    oles
    0.44
    ile
    0.43
    oodle
    0.43
     align
    0.42
    ialize
    0.41
    ocrine
    0.41
    ilers
    0.41
     onPress
    0.40
     (
    0.39
    Activations Density 0.000%

    No Known Activations