© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12227
    Prev
    Next
    INDEX
    Explanations

    learn approved information

    np_acts-logits-general · gemini-2.5-flash-lite

    starts of sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ৮
    0.46
    Lr
    0.46
    BIT
    0.45
    ۷
    0.45
    UINT
    0.44
    ১
    0.44
    ८
    0.44
    ۸
    0.44
    
    0.44
    RT
    0.44
    POSITIVE LOGITS
     volant
    0.49
    Indic
    0.48
     Indones
    0.48
     Indic
    0.48
    源代码
    0.47
    现代
    0.46
    茷
    0.46
    ాలతో
    0.46
     végét
    0.45
     Antip
    0.45
    Activations Density 0.003%

    No Known Activations