© 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. 54436
    Prev
    Next
    INDEX
    Explanations

    sequence under test

    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
    덮
    0.47
    m
    0.45
    𝘀
    0.44
    table
    0.42
    ties
    0.42
    前に
    0.41
     틀
    0.41
     ți
    0.41
     Libro
    0.41
     prefabricated
    0.41
    POSITIVE LOGITS
     hopper
    0.48
    UnderTest
    0.47
    Breakpoint
    0.45
     raggiungere
    0.45
     opcode
    0.43
     ferrug
    0.42
     oxidación
    0.42
    ilege
    0.41
     eigenvalue
    0.39
     reformulation
    0.39
    Activations Density 0.001%

    No Known Activations