© 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. 40-GEMMASCOPE-2-RES-262K
    7. 135062
    Prev
    Next
    INDEX
    Explanations

    concepts and specific entities

    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
     Considered
    0.46
    唪
    0.46
    दार
    0.45
    গুপ্ত
    0.44
     Unfortunately
    0.43
    autre
    0.43
     формула
    0.42
    neurs
    0.41
     Usually
    0.40
     जातात
    0.40
    POSITIVE LOGITS
     memory
    0.42
    កំណ
    0.39
    蠻
    0.38
     innovación
    0.37
     radically
    0.37
     memória
    0.36
     footprint
    0.36
    介绍了
    0.36
    Memory
    0.35
     tremendous
    0.35
    Activations Density 0.003%

    No Known Activations