© 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. 216586
    Prev
    Next
    INDEX
    Explanations

    spooky pumpkins

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

    questions about faith and stories

    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
    ם
    0.48
    ИН
    0.47
    ряз
    0.47
    されて
    0.46
     espl
    0.46
    エラー
    0.46
     परिस
    0.46
     об
    0.46
    ˒
    0.45
     дости
    0.45
    POSITIVE LOGITS
    لاميذ
    0.49
     hail
    0.48
     dzieci
    0.48
    ReturnValue
    0.46
     vaccinated
    0.46
     meat
    0.45
     Olivia
    0.45
     byteArray
    0.44
    Flow
    0.43
    Yield
    0.43
    Activations Density 0.000%

    No Known Activations