© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18022
    Prev
    Next
    INDEX
    Explanations

    userData Array, Station SSID, Absolute Decline

    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
     the
    0.42
     benign
    0.40
     depressing
    0.40
    ண்ண
    0.40
    nias
    0.40
    <start_of_image>
    0.40
     marginally
    0.40
     weakly
    0.39
     throughout
    0.38
     remotely
    0.38
    POSITIVE LOGITS
     имеет
    0.51
     debería
    0.49
     ustaw
    0.48
     dará
    0.48
     ú
    0.48
     حا
    0.48
     купа
    0.48
     obsług
    0.47
     اع
    0.47
     Grom
    0.47
    Activations Density 0.001%

    No Known Activations