© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 55056
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hosting
    0.36
     Rech
    0.36
    臓
    0.35
     Bridal
    0.35
     Lept
    0.35
     DEVICE
    0.34
    ')",
    0.34
     nồi
    0.34
     *)
    0.34
     চু
    0.34
    POSITIVE LOGITS
    dokument
    0.43
    ਿਲ
    0.41
     asynchronously
    0.40
    Ꮣ
    0.39
    torn
    0.38
     valamint
    0.38
    timeline
    0.38
     mundane
    0.37
    یداری
    0.37
     delusion
    0.37
    Activations Density 0.011%

    No Known Activations