© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 26321
    Prev
    Next
    INDEX
    Explanations

    elaborate weddings, keeping safe

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

    relationship states revisions

    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
     absorb
    0.48
     abre
    0.43
     আন্দ
    0.43
     Abschnitt
    0.43
     раздел
    0.42
    錘
    0.42
    ⬮
    0.42
     aktivieren
    0.41
    )”
    0.41
     වීම
    0.41
    POSITIVE LOGITS
    ͞
    0.52
    relationship
    0.52
     वह
    0.50
    ция
    0.50
    etik
    0.49
    oterapia
    0.48
     relationship
    0.48
    one
    0.47
    going
    0.47
    orong
    0.47
    Activations Density 0.000%

    No Known Activations