© 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. 12189
    Prev
    Next
    INDEX
    Explanations

    super power, VR, bred

    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
    ه
    0.50
    ה
    0.47
    ів
    0.47
    ్
    0.46
    𝗲
    0.46
    ার্থী
    0.46
    ن
    0.46
     сот
    0.44
    ر
    0.44
     ότι
    0.43
    POSITIVE LOGITS
     animales
    0.49
     nieder
    0.47
     polygonal
    0.47
     Bolog
    0.47
     Madeira
    0.47
     Duf
    0.47
     Ferté
    0.47
     anatom
    0.46
     Oiseau
    0.46
     cumplir
    0.46
    Activations Density 0.005%

    No Known Activations