© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 39527
    Prev
    Next
    INDEX
    Explanations

    average growth or trend

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

    use or produce information

    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
     diariamente
    0.55
     HTMLSc
    0.52
     alcançar
    0.49
     تناول
    0.49
     வெறு
    0.49
     اختلاف
    0.48
     ڈ
    0.47
    ؟.
    0.47
     aslında
    0.47
    אם
    0.46
    POSITIVE LOGITS
     relevant
    0.48
     qualification
    0.47
     haven
    0.45
     both
    0.44
     hasn
    0.44
     qualifications
    0.43
     great
    0.43
    cone
    0.42
     spectrom
    0.41
    ̒
    0.41
    Activations Density 0.000%

    No Known Activations