© 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. 142414
    Prev
    Next
    INDEX
    Explanations

    years, months, million, daily, 80

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

    mythological or being able

    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
    🥫
    0.58
    )
    0.54
     ɖ
    0.53
     प्रका
    0.52
     )
    0.52
     &#
    0.52
     पुरे
    0.52
     東京
    0.50
     داری
    0.49
     腰
    0.49
    POSITIVE LOGITS
    édez
    0.47
    ступи
    0.44
    இவ்வாறு
    0.44
    Canvas
    0.42
    Destroy
    0.42
     обнов
    0.41
    центри
    0.41
    рем
    0.41
    andered
    0.40
     unsettled
    0.40
    Activations Density 0.000%

    No Known Activations