© 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. 202738
    Prev
    Next
    INDEX
    Explanations

    conservation status

    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
     apenas
    0.54
     ofrece
    0.51
     뿐
    0.51
    adece
    0.51
     vuole
    0.48
    Artifact
    0.48
     Está
    0.48
     ৯০
    0.48
    வடிக்க
    0.47
     esté
    0.47
    POSITIVE LOGITS
     subsequence
    0.44
     primal
    0.44
     chl
    0.44
     complexes
    0.43
    汝
    0.43
    μ
    0.42
     subsequ
    0.42
     variational
    0.41
    pairwise
    0.41
     unim
    0.41
    Activations Density 0.002%

    No Known Activations