© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54285
    Prev
    Next
    INDEX
    Explanations

    relatively low

    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
    Neces
    0.51
    ዩ
    0.47
     וו
    0.46
    å
    0.46
    、
    0.45
    㐬
    0.45
    ůj
    0.44
    ö
    0.44
    ismillahirrah
    0.43
    direito
    0.43
    POSITIVE LOGITS
     cycle
    0.46
     compaction
    0.46
     insertion
    0.45
     cycles
    0.45
     amplification
    0.43
     relief
    0.43
     strain
    0.43
     bowling
    0.42
     fluctuations
    0.42
     within
    0.41
    Activations Density 0.032%

    No Known Activations