© 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. 189395
    Prev
    Next
    INDEX
    Explanations

    formats, conclude sales

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

    Blackwood Manor roses

    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
     Pursuant
    0.49
    ow
    0.49
     NHL
    0.49
    j
    0.48
     Acura
    0.46
    NHL
    0.45
     Minn
    0.44
    诸多
    0.44
    b
    0.43
    ximately
    0.43
    POSITIVE LOGITS
     масси
    0.53
     пово
    0.51
     தெரிவித்துள்ளது
    0.50
     arched
    0.50
     അവത
    0.47
     وتم
    0.46
     zupeł
    0.46
     mesmerizing
    0.45
     ዘዴ
    0.45
     combinaison
    0.44
    Activations Density 0.001%

    No Known Activations