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

    Neuronpedia

    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. 3637
    Prev
    Next
    INDEX
    Explanations

    questions followed by explanations

    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
    齣
    0.42
     ეს
    0.41
    𝘬
    0.40
     ዋና
    0.40
    atenated
    0.40
    掴
    0.39
     genus
    0.39
     பெரும்பாலான
    0.38
    上記の
    0.38
     അവസ്ഥ
    0.38
    POSITIVE LOGITS
     protože
    0.43
     आणि
    0.42
     porque
    0.40
     because
    0.40
     omdat
    0.40
    V
    0.40
     потому
    0.39
     અને
    0.38
     which
    0.37
    FirebaseAuth
    0.37
    Activations Density 0.148%

    No Known Activations