© 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. 218631
    Prev
    Next
    INDEX
    Explanations

    fingerprint christmas; Emperor; attorneys

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

    making things complex or easier

    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
     yüks
    0.44
     wonderland
    0.44
     समाधान
    0.43
    gerufen
    0.42
     균
    0.42
    verfahren
    0.41
     کنیم
    0.40
    weł
    0.40
     centrifuged
    0.40
    alahkan
    0.40
    POSITIVE LOGITS
    Shi
    0.48
    𝑭
    0.48
    wne
    0.47
    本書
    0.46
    tweets
    0.46
    
    0.46
    শি
    0.44
     Fli
    0.44
     त्रि
    0.44
    buyer
    0.44
    Activations Density 0.001%

    No Known Activations