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

    Neuronpedia

    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. 84146
    Prev
    Next
    INDEX
    Explanations

    Wi-Fi, boards, teammates

    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
     INE
    0.46
    氳
    0.43
     AAS
    0.42
     theres
    0.42
    轳
    0.41
    菘
    0.41
     आराम
    0.41
     leche
    0.40
     austenite
    0.40
     TAS
    0.40
    POSITIVE LOGITS
    ή
    0.47
    osp
    0.46
     десять
    0.44
    nos
    0.44
    permitted
    0.43
     नावा
    0.43
     высокой
    0.43
     ၁
    0.43
    unjungi
    0.43
    ˁ
    0.42
    Activations Density 0.006%

    No Known Activations