© 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. 181546
    Prev
    Next
    INDEX
    Explanations

    money and return costs

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

    wire wrapped

    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
    яс
    0.47
    тово
    0.46
     innovative
    0.44
    цтва
    0.44
    ма
    0.44
    мад
    0.43
    мур
    0.42
    σ
    0.42
     unmodified
    0.41
    п
    0.41
    POSITIVE LOGITS
     ફ
    0.46
    membre
    0.43
    ately
    0.43
    前面
    0.43
     membre
    0.42
     عضو
    0.41
     divisional
    0.41
     Divisional
    0.40
    อาจ
    0.40
     फ्रांस
    0.39
    Activations Density 0.001%

    No Known Activations