© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5784
    Prev
    Next
    INDEX
    Explanations

    defensive performance metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    western
    1.85
     reapp
    1.85
     cale
    1.83
     Linton
    1.82
     dimmed
    1.79
    finale
    1.78
    кали
    1.76
    雏
    1.75
    しばらく
    1.75
    village
    1.75
    POSITIVE LOGITS
    ас
    1.12
     memcpy
    1.07
     strcpy
    1.03
    맬
    0.99
     uintptr
    0.95
    ATURE
    0.94
    ITATE
    0.93
    Ằ
    0.93
    IDENTIAL
    0.93
     TORT
    0.92
    Activations Density 0.083%

    No Known Activations