© 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. 204643
    Prev
    Next
    INDEX
    Explanations

    universal concepts or properties

    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
    t
    0.48
     descargar
    0.42
    약
    0.42
    عمال
    0.41
    nda
    0.41
     whirlpool
    0.40
     luxuries
    0.40
    1
    0.40
    ève
    0.40
     matériel
    0.39
    POSITIVE LOGITS
     ਰ
    0.58
     ऋषि
    0.47
     亻
    0.46
    ALING
    0.46
     ರೂ
    0.45
     रोजी
    0.45
     Arrang
    0.44
    CLUDING
    0.44
    elist
    0.44
     ವ
    0.43
    Activations Density 0.005%

    No Known Activations