© 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-65K
    7. 36150
    Prev
    Next
    INDEX
    Explanations

    illustrative hypothetical Indian

    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_65k_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
    App
    0.52
    Payment
    0.52
    দের
    0.47
    %%
    0.47
    ի
    0.47
    <0xAD>
    0.46
    Challenge
    0.46
    Polic
    0.46
    Gender
    0.46
    们
    0.46
    POSITIVE LOGITS
     overburden
    0.50
     ancestry
    0.49
    revalidator
    0.45
     trellis
    0.44
     ascorbic
    0.43
     shabd
    0.43
     tolerances
    0.43
    ampunk
    0.43
     overall
    0.42
     overt
    0.42
    Activations Density 0.032%

    No Known Activations