© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3279
    Prev
    Next
    INDEX
    Explanations

    modelPyTorch Matplotlib files Jasper Spark

    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
    泄
    0.86
    mina
    0.80
     clopen
    0.79
    نساء
    0.78
     renegoti
    0.76
    творе
    0.74
    mn
    0.73
     femminile
    0.73
    ญิง
    0.72
    键
    0.69
    POSITIVE LOGITS
     Jasper
    1.61
     Spark
    1.55
     Philip
    1.53
     Tag
    1.44
     DG
    1.44
     Dag
    1.42
     PSC
    1.36
     Philips
    1.34
     Epic
    1.34
     Vega
    1.31
    Activations Density 0.082%

    No Known Activations