© 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. 91849
    Prev
    Next
    INDEX
    Explanations

    something that feels wrong

    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
    J
    0.51
    -
    0.46
    St
    0.45
     a
    0.44
    MA
    0.44
    m
    0.44
     वि
    0.43
    miss
    0.42
    l
    0.41
    CP
    0.41
    POSITIVE LOGITS
     caloric
    0.49
     tuleb
    0.49
     能
    0.45
     pendapatan
    0.45
    收入
    0.44
     इनकी
    0.44
     detn
    0.44
     armature
    0.43
     ProductName
    0.43
    氻
    0.43
    Activations Density 0.010%

    No Known Activations