© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 120155
    Prev
    Next
    INDEX
    Explanations

    obfuscation

    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
     desenho
    0.60
    و
    0.59
    ส์
    0.58
    س
    0.58
     Lemma
    0.57
    с
    0.57
    th
    0.56
     Derecho
    0.55
    െ
    0.55
    𝘦
    0.54
    POSITIVE LOGITS
    Drop
    0.60
    Ii
    0.55
    twin
    0.55
    Twin
    0.55
    Shr
    0.53
    Sar
    0.53
    Therm
    0.52
    Ally
    0.50
    Muslim
    0.50
     Бүген
    0.50
    Activations Density 0.000%

    No Known Activations