© 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-262K
    7. 75412
    Prev
    Next
    INDEX
    Explanations

    systems, definitions, rules

    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
    ίας
    0.53
    ̀i
    0.45
    é
    0.44
    ואה
    0.43
    ιού
    0.43
    र्यंत
    0.42
     conflicting
    0.41
     решил
    0.41
    ลล์
    0.41
    лли
    0.41
    POSITIVE LOGITS
    2
    0.44
    }}+
    0.42
    Terminology
    0.42
    4
    0.42
     定义
    0.42
    9
    0.42
    7
    0.41
    ，
    0.40
    purpose
    0.40
    Definitions
    0.40
    Activations Density 0.004%

    No Known Activations