© 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. 29235
    Prev
    Next
    INDEX
    Explanations

    ostensibly, presumably, reportedly

    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
    给
    0.45
     получается
    0.41
     بنابراین
    0.41
    可在
    0.39
     therefore
    0.38
    Ctrl
    0.38
     slur
    0.38
    Goto
    0.37
    Cheap
    0.37
    }}}}$
    0.36
    POSITIVE LOGITS
     ostensibly
    0.52
     presumably
    0.50
     undisclosed
    0.48
     demeanor
    0.47
     Presumably
    0.46
     comport
    0.46
     मनाने
    0.45
     rumored
    0.45
     intending
    0.44
     reportedly
    0.44
    Activations Density 0.024%

    No Known Activations