© 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. 113703
    Prev
    Next
    INDEX
    Explanations

    diverse inspirations holder semi percent your

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

    explaining velocity, lying, risk

    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
     են
    0.44
    Bp
    0.43
     minif
    0.43
     drive
    0.42
     during
    0.41
     fastball
    0.41
     mathrm
    0.41
     b
    0.41
     det
    0.41
     dehydrogenase
    0.41
    POSITIVE LOGITS
    этому
    0.50
    ટો
    0.46
    谈
    0.45
    чём
    0.45
    ومه
    0.44
    pathname
    0.44
     تلك
    0.44
    ர்க
    0.43
    ன்ற
    0.43
    ன்ப
    0.43
    Activations Density 0.000%

    No Known Activations