© 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. 20187
    Prev
    Next
    INDEX
    Explanations

    Probe assumptions

    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
    Très
    0.43
    Wonderful
    0.42
    仠
    0.42
    烃
    0.42
     Maintenant
    0.41
    䄪
    0.41
    ÁN
    0.40
    徙
    0.40
    Selon
    0.40
     Cré
    0.39
    POSITIVE LOGITS
     jika
    0.47
     default
    0.46
     clearly
    0.45
     element
    0.44
     if
    0.44
     defin
    0.43
    default
    0.43
     freeze
    0.43
     freezing
    0.43
     frozen
    0.42
    Activations Density 0.000%

    No Known Activations