© 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. 115043
    Prev
    Next
    INDEX
    Explanations

    0800 555111 or 101

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

    Amazon sellers and origins

    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
    MBOLS
    0.42
     domenica
    0.41
    াবন
    0.40
    逆に
    0.40
     نوفمبر
    0.39
     Simultaneously
    0.38
     [];
    0.38
     dünya
    0.38
     simult
    0.37
     sekaligus
    0.37
    POSITIVE LOGITS
    炁
    0.52
     мотор
    0.50
     вмі
    0.45
    七
    0.45
     Virgen
    0.44
     자기
    0.43
     anhyd
    0.43
     garam
    0.43
    HeaderText
    0.42
     térm
    0.41
    Activations Density 0.000%

    No Known Activations