© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 160471
    Prev
    Next
    INDEX
    Explanations

    depending on

    np_acts-logits-general · gemini-2.5-flash-lite

    brutal, efficient, promising descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     könny
    0.51
     吴
    0.48
     ford
    0.48
     wissenschaft
    0.46
     algebraica
    0.45
     hipótesis
    0.45
     biopsy
    0.44
     hypothes
    0.43
     unge
    0.43
     başta
    0.42
    POSITIVE LOGITS
    ቛ
    0.54
    ፴
    0.52
     locals
    0.49
    लट
    0.47
    ار
    0.47
    locals
    0.47
    χύ
    0.47
    ग
    0.45
     Locals
    0.45
    র
    0.45
    Activations Density 0.000%

    No Known Activations