© 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. 16-GEMMASCOPE-2-RES-262K
    7. 42746
    Prev
    Next
    INDEX
    Explanations

    transition, dry, national, identifying

    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_16_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
     sınır
    0.50
    焜
    0.49
     angegeben
    0.48
     kontroller
    0.47
     Ashok
    0.47
     المُ
    0.47
     Erweiter
    0.47
     கலோரிகள்
    0.47
     as
    0.46
     LCA
    0.46
    POSITIVE LOGITS
    לות
    0.58
    Ь
    0.52
    呓
    0.52
     tragic
    0.51
     temptation
    0.50
    ạc
    0.49
    یب
    0.49
    고사
    0.48
     tempest
    0.48
     detective
    0.47
    Activations Density 0.000%

    No Known Activations