© 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. 202620
    Prev
    Next
    INDEX
    Explanations

    Anycubic claims

    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
    วง
    0.46
     nomm
    0.45
    Dé
    0.45
    璉
    0.44
    Eff
    0.42
    Chois
    0.42
     extractive
    0.42
    麿
    0.42
    бліоте
    0.41
    Levels
    0.41
    POSITIVE LOGITS
     ससुराल
    0.49
     применять
    0.49
     Cantonese
    0.48
    |,
    0.47
    lijn
    0.45
     к
    0.45
    countdown
    0.45
    ӳ
    0.45
     руковод
    0.44
     Ξ
    0.44
    Activations Density 0.001%

    No Known Activations