© 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. 108235
    Prev
    Next
    INDEX
    Explanations

    specialization or adaptation

    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
     vertebrates
    0.54
    󰡔
    0.49
     multinationals
    0.48
     calculi
    0.45
     सीड्स
    0.44
     tumors
    0.43
     nodules
    0.43
     pathophysiology
    0.43
     quilts
    0.42
     prefs
    0.41
    POSITIVE LOGITS
     Without
    0.46
     Radford
    0.44
     without
    0.44
     Smith
    0.43
     Temperature
    0.41
     Jane
    0.41
    :<
    0.41
     ABCD
    0.41
    onn
    0.40
     ohne
    0.40
    Activations Density 0.007%

    No Known Activations