© 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. 40598
    Prev
    Next
    INDEX
    Explanations

    description of contents or location

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

    foundational descriptors and actions

    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
    汽車
    0.41
    }{
    0.39
    状況
    0.38
     cytoplas
    0.38
    বেশ
    0.38
     अस्तित्व
    0.38
     tossing
    0.37
    模様
    0.37
    itum
    0.37
     साप्ताहिक
    0.37
    POSITIVE LOGITS
    </h1>
    0.49
     liberate
    0.44
    מיד
    0.44
    contre
    0.42
    ಾಲ
    0.42
     coincidence
    0.41
    АО
    0.38
    पढ़
    0.38
    BACK
    0.37
    Checked
    0.37
    Activations Density 0.000%

    No Known Activations