© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 112483
    Prev
    Next
    INDEX
    Explanations

    unraveling, desert, spectrum, judge

    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
    テント
    0.48
     specjal
    0.46
     basically
    0.44
     B
    0.44
     questioning
    0.43
     چندین
    0.43
     توسط
    0.42
    anson
    0.42
     clinically
    0.42
    ainya
    0.41
    POSITIVE LOGITS
    ్రమ
    0.55
    })$.
    0.52
    рока
    0.51
    లీ
    0.48
    ukhov
    0.48
    दंड
    0.47
    리
    0.47
    녹
    0.46
    рино
    0.46
    敺
    0.44
    Activations Density 0.001%

    No Known Activations