© 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. 55393
    Prev
    Next
    INDEX
    Explanations

    against

    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
    ية
    0.74
    чках
    0.70
    و
    0.70
    ):["
    0.67
    )—
    0.62
    ки
    0.61
    ام
    0.61
    ку
    0.61
    वळ
    0.61
    ാ
    0.61
    POSITIVE LOGITS
     Against
    1.06
     against
    1.05
    against
    0.99
    Against
    0.92
    is
    0.85
     l
    0.81
    y
    0.80
    t
    0.80
     против
    0.79
     gegen
    0.78
    Activations Density 0.032%

    No Known Activations