© 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. 124395
    Prev
    Next
    INDEX
    Explanations

    Worst enemies, no credit

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

    setting up descriptions or sentences

    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
     муниципа
    0.52
    हुआ
    0.44
    手中的
    0.43
    昆
    0.43
     perdita
    0.42
    طبيق
    0.42
    Sports
    0.42
    hetam
    0.41
     impactos
    0.40
     emitida
    0.40
    POSITIVE LOGITS
     $,
    0.52
     ನಡುವ
    0.51
     रस्सी
    0.49
     সঙ্ক
    0.49
    Texture
    0.46
     పెట్ట
    0.46
     শীত
    0.45
     정보를
    0.44
     foreground
    0.44
    名称
    0.44
    Activations Density 0.002%

    No Known Activations