© 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. 134608
    Prev
    Next
    INDEX
    Explanations

    family members, names, or technical names

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

    instructions, advice, or lists

    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
     বহু
    0.47
    กัน
    0.47
    하며
    0.46
     যাত্রা
    0.45
    之时
    0.44
    కు
    0.43
    했고
    0.43
    과
    0.43
     als
    0.43
    টিও
    0.43
    POSITIVE LOGITS
     lysate
    0.52
    recover
    0.47
     threatening
    0.46
     retorted
    0.46
    recovered
    0.45
    khar
    0.45
     threaten
    0.44
     hampered
    0.44
     thwarted
    0.43
    sub
    0.43
    Activations Density 0.000%

    No Known Activations