© 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. 190387
    Prev
    Next
    INDEX
    Explanations

    company, discovery, gas, literature, entry

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

    kid's date

    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
     chol
    0.44
    十四
    0.43
    దా
    0.43
    呎
    0.43
     tints
    0.42
     блок
    0.41
    Ná
    0.41
     whisky
    0.41
     tinted
    0.41
    十一
    0.41
    POSITIVE LOGITS
    ²)
    0.52
    anne
    0.48
    br
    0.46
    capacitor
    0.46
     эсеп
    0.46
    をと
    0.45
    ilerin
    0.45
    捛
    0.45
    geç
    0.45
    att
    0.44
    Activations Density 0.000%

    No Known Activations