© 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. 221795
    Prev
    Next
    INDEX
    Explanations

    words that precede descriptors

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

    section headings and topics

    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
     fato
    0.46
    かを
    0.45
     radii
    0.45
     revise
    0.44
     perkembangan
    0.44
    })(\
    0.43
     ਨੂੰ
    0.43
     ძალი
    0.42
     sceGu
    0.42
    युद्ध
    0.42
    POSITIVE LOGITS
    嵌套
    0.46
     herein
    0.45
     Murdock
    0.45
     Nested
    0.44
     स्वाभाविक
    0.42
    five
    0.42
    biet
    0.42
    ጿ
    0.41
     समर्पित
    0.40
    针
    0.40
    Activations Density 0.001%

    No Known Activations