© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79765
    Prev
    Next
    INDEX
    Explanations

    ** and headings

    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
    고
    0.48
    ی
    0.48
    意味着
    0.43
    Beginning
    0.43
    졌
    0.41
    参与
    0.40
    یک
    0.40
    forth
    0.40
    ཐ
    0.40
     yine
    0.39
    POSITIVE LOGITS
     amenazas
    0.55
     spezi
    0.49
     ねえ
    0.46
     Lactobacillus
    0.46
    chandise
    0.46
    紊
    0.45
    ꜜ
    0.44
     tolerant
    0.44
     kinda
    0.44
    apayati
    0.44
    Activations Density 0.000%

    No Known Activations