© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 10
    Prev
    Next
    INDEX
    Explanations

    context information labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_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
     Cay
    1.20
     Adams
    1.10
     COS
    1.08
     Tay
    1.07
     Hay
    1.05
     코
    1.03
     Сим
    1.03
    코
    1.02
     Mayer
    1.02
    Cay
    1.01
    POSITIVE LOGITS
    ervo
    0.68
    แข็ง
    0.67
     LSR
    0.67
    봇
    0.66
    匪
    0.64
    强的
    0.63
     McInt
    0.63
    辮
    0.63
    院校
    0.63
    edio
    0.62
    Activations Density 1.065%

    No Known Activations