© 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-262K
    7. 172910
    Prev
    Next
    INDEX
    Explanations

    entities and relationships

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

    short video clips

    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_262k_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
     PAOK
    0.57
    amyl
    0.50
     Sardegna
    0.50
    𝄞
    0.49
    spectra
    0.48
     droid
    0.48
    រក
    0.48
    させた
    0.48
    
    0.48
    bindingFields
    0.47
    POSITIVE LOGITS
    v
    0.52
    Cot
    0.49
    h
    0.48
    Things
    0.48
    Anderson
    0.48
    Cap
    0.46
    Cache
    0.46
    ProductImages
    0.44
    Body
    0.43
     Anderson
    0.42
    Activations Density 0.001%

    No Known Activations