© 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. 64601
    Prev
    Next
    INDEX
    Explanations

    On Pinterest

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

    numbers, punctuation, and phrases

    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
    be
    0.58
    ü
    0.57
    ven
    0.55
    üm
    0.55
    ate
    0.55
    oum
    0.54
    le
    0.54
    oru
    0.54
    ru
    0.53
    ouro
    0.53
    POSITIVE LOGITS
     शायद
    0.48
     chłop
    0.46
    猥
    0.45
    🪴
    0.45
     táo
    0.44
     ಹೇಳಿದರು
    0.44
     deprecated
    0.44
     प्रतिनिधित्व
    0.44
    দ্দিক
    0.44
     Tamaño
    0.44
    Activations Density 0.000%

    No Known Activations