© 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. 25758
    Prev
    Next
    INDEX
    Explanations

    punitive damages, insider issues, malware, resolve issues

    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
     vuoi
    0.48
     fucked
    0.47
    ໕
    0.46
     shitty
    0.45
     нужда
    0.45
     visant
    0.44
     казах
    0.43
     chiede
    0.43
     povinn
    0.43
     légumes
    0.42
    POSITIVE LOGITS
    the
    0.45
     even
    0.45
    ・
    0.44
    d
    0.42
    W
    0.42
    Manufacturers
    0.41
    US
    0.40
    ING
    0.40
    B
    0.40
    include
    0.39
    Activations Density 0.001%

    No Known Activations