© 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-65K
    7. 4815
    Prev
    Next
    INDEX
    Explanations

    phrase, application, particularly

    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_65k_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
    볍
    1.04
     necessari
    0.90
     iniciar
    0.81
     préalable
    0.80
    rinsic
    0.80
     hipótes
    0.78
     possibilità
    0.76
     legitt
    0.75
    暂
    0.74
    seeking
    0.73
    POSITIVE LOGITS
     HDTV
    1.84
     alot
    1.65
     tapes
    1.63
    复杂的
    1.62
     TVs
    1.62
     mange
    1.61
     pudding
    1.56
     clocks
    1.56
     pictures
    1.56
     hubby
    1.55
    Activations Density 0.057%

    No Known Activations