© 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-262K
    7. 44221
    Prev
    Next
    INDEX
    Explanations

    neighborhood, password, Bard, public, broadened, changes

    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
     bertanya
    0.52
     menilai
    0.48
     upang
    0.43
    윳
    0.43
     perempt
    0.43
     chá
    0.43
     náz
    0.42
     opa
    0.42
     پیسې
    0.42
     sepatu
    0.41
    POSITIVE LOGITS
     utilises
    0.46
    cedure
    0.44
    mination
    0.44
    被
    0.43
    使用
    0.42
     femelle
    0.42
    一部分
    0.42
    用户
    0.42
    peration
    0.41
    大部分
    0.41
    Activations Density 0.004%

    No Known Activations