© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24084
    Prev
    Next
    INDEX
    Explanations

    introducing specific concepts

    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
    руп
    0.45
     मिर
    0.42
    રણ
    0.41
     земель
    0.40
     запо
    0.39
    Salir
    0.39
    Ꮘ
    0.36
    TabText
    0.36
    lamak
    0.36
     devoting
    0.36
    POSITIVE LOGITS
     kong
    0.38
    aniye
    0.38
     Wight
    0.38
     excellent
    0.37
     much
    0.37
     intéressant
    0.37
     concerned
    0.37
    𝒍
    0.37
    不等
    0.37
    ensitivity
    0.36
    Activations Density 0.003%

    No Known Activations