© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10323
    Prev
    Next
    INDEX
    Explanations

    distance and time measurements

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

    cooking methods

    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_40_width_16k_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
    福祉
    0.41
     ڈ
    0.40
    Fetching
    0.39
     στι
    0.39
     tractable
    0.38
    ”?
    0.38
    แฟ
    0.38
    istent
    0.37
     appass
    0.37
    Ý
    0.37
    POSITIVE LOGITS
    არა
    0.43
    variety
    0.41
     assaulted
    0.41
     verbally
    0.39
     साढ़े
    0.39
    orang
    0.38
    entrance
    0.38
     demolished
    0.38
     campgrounds
    0.38
    बिनेट
    0.37
    Activations Density 0.021%

    No Known Activations