© 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. 31-GEMMASCOPE-2-RES-262K
    4. 2129
    Prev
    Next
    INDEX
    Explanations

    multilingual content

    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
     bzw
    0.23
    /
    0.21
     \
    0.20
    вер
    0.18
     
    0.18
    இ
    0.18
     OS
    0.17
    United
    0.17
     Albums
    0.17
    中
    0.17
    POSITIVE LOGITS
     beginnen
    0.23
    скільки
    0.21
    гает
    0.21
    addassa
    0.20
     випадку
    0.20
     sientes
    0.20
    ahami
    0.19
     सुझाव
    0.19
    钡
    0.19
     triste
    0.19
    Activations Density 0.003%

    No Known Activations