© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138385
    Prev
    Next
    INDEX
    Explanations

    reasoned account

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     B
    0.52
     cam
    0.50
     January
    0.48
     December
    0.48
     To
    0.48
     radiation
    0.48
     Kim
    0.47
     Kam
    0.46
     F
    0.46
     Cam
    0.46
    POSITIVE LOGITS
    жда
    0.50
    fiscal
    0.49
    RUP
    0.48
    ॉप
    0.46
    tig
    0.46
    탉
    0.46
    support
    0.45
     án
    0.45
    REDIRECT
    0.44
    𒌨
    0.44
    Activations Density 0.002%

    No Known Activations