© 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. 99479
    Prev
    Next
    INDEX
    Explanations

    plateau August audience Story integers services

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

    asset, journey, cause

    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
    टाम
    0.55
    Ң
    0.54
    間
    0.53
    on
    0.52
     Temps
    0.50
    ába
    0.47
    ้น
    0.47
     Releases
    0.47
    দেবের
    0.46
    H
    0.46
    POSITIVE LOGITS
     sagittal
    0.47
     entanglement
    0.46
     applicability
    0.44
     decyz
    0.44
     рішення
    0.44
     egli
    0.43
     керів
    0.43
    Transicao
    0.43
     Questo
    0.42
     திட்டம்
    0.42
    Activations Density 0.000%

    No Known Activations