© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202339
    Prev
    Next
    INDEX
    Explanations

    ways, visualize, offense

    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_262k_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
    profit
    0.47
    tu
    0.44
    hon
    0.43
    tuk
    0.43
    t
    0.43
     favourite
    0.42
    ttk
    0.42
    ठे
    0.41
    तु
    0.41
    દ
    0.41
    POSITIVE LOGITS
    Issuer
    0.49
    映射
    0.47
     intermédiaire
    0.46
     destrucción
    0.45
     đ
    0.45
     sangre
    0.44
     đáp
    0.44
    BILL
    0.44
     tranch
    0.43
     mapas
    0.43
    Activations Density 0.011%

    No Known Activations