© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 164693
    Prev
    Next
    INDEX
    Explanations

    specific entities or definitions

    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_40_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
    शाही
    0.43
     Wart
    0.42
    悵
    0.42
     hated
    0.41
     wars
    0.40
    不但
    0.40
     измене
    0.39
     despised
    0.39
    }+...
    0.39
     Kale
    0.38
    POSITIVE LOGITS
    Downtown
    0.43
    refreshToken
    0.38
    <0x93>
    0.37
    ouer
    0.36
     Downtown
    0.36
    ᴱ
    0.35
    Ø
    0.35
    utin
    0.35
    Allium
    0.35
     Архі
    0.34
    Activations Density 0.000%

    No Known Activations