© 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. 188038
    Prev
    Next
    INDEX
    Explanations

    relations, site, galaxy, durations

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

    even when, visually shows, depending on

    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
    IENTE
    0.54
    लास
    0.52
    하십시오
    0.52
    ೀರ
    0.50
    লিন
    0.50
    Ժ
    0.50
    ᙱ
    0.49
    ⁻
    0.48
    ındadır
    0.48
    λος
    0.48
    POSITIVE LOGITS
    ’
    0.46
     Before
    0.43
     it
    0.42
    trim
    0.42
    t
    0.42
     We
    0.40
     K
    0.40
     augmente
    0.40
    ric
    0.40
     corrected
    0.39
    Activations Density 0.000%

    No Known Activations