© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53865
    Prev
    Next
    INDEX
    Explanations

    bears hunting

    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_65k_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
     furt
    0.46
    Philos
    0.45
     Bios
    0.42
     letzt
    0.42
     اد
    0.42
    戦争
    0.41
    필
    0.40
     konflikt
    0.39
     uwagę
    0.39
     전쟁
    0.39
    POSITIVE LOGITS
     РФ
    0.48
     confertim
    0.47
     approximating
    0.45
    েন্ট
    0.44
     obič
    0.44
     quilted
    0.43
    冂
    0.42
     नियमित
    0.42
    ্যালেঞ্জ
    0.42
    স্তাফ
    0.42
    Activations Density 0.022%

    No Known Activations