© 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. 3193
    Prev
    Next
    INDEX
    Explanations

    framework, huevo, rest

    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
    PU
    1.51
     pomegranate
    1.49
    깅
    1.46
     qq
    1.45
     Aleksandar
    1.43
     sunflowers
    1.42
     rgb
    1.42
    ściej
    1.41
     وده
    1.40
     Parisi
    1.39
    POSITIVE LOGITS
     contingencies
    0.82
     this
    0.71
    ---
    0.70
     master
    0.67
    นี้
    0.66
     Time
    0.65
     today
    0.65
    ona
    0.64
     which
    0.64
     prospective
    0.64
    Activations Density 0.144%

    No Known Activations