© 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. 120484
    Prev
    Next
    INDEX
    Explanations

    enddefensiveprotein

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

    context: conversations and instructions

    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
     sirve
    0.57
    ))]
    0.50
     serve
    0.48
     Yu
    0.44
     totiž
    0.44
     पनि
    0.43
     cũng
    0.43
     serves
    0.42
    stan
    0.42
     %>%
    0.42
    POSITIVE LOGITS
    قة
    0.53
    ونت
    0.50
    нена
    0.50
    ום
    0.49
    ک
    0.49
    бовать
    0.48
    یس
    0.48
    бах
    0.46
    Reasons
    0.46
    کان
    0.46
    Activations Density 0.000%

    No Known Activations