© 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. 30541
    Prev
    Next
    INDEX
    Explanations

    all kinds of

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

    ` without `, ` hindered `, `desired`

    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
    čenje
    0.46
    oną
    0.46
    Lä
    0.45
    𝓪
    0.44
     Comenz
    0.44
    १८६
    0.43
    Полу
    0.42
    iyordu
    0.41
     Органи
    0.41
     १८४
    0.41
    POSITIVE LOGITS
     জন্মদিন
    0.38
    '
    0.38
     anschauen
    0.38
     GUI
    0.37
     flips
    0.36
     عند
    0.36
     footprint
    0.35
     fixes
    0.35
     dams
    0.35
    ”
    0.35
    Activations Density 0.000%

    No Known Activations