© 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. 79630
    Prev
    Next
    INDEX
    Explanations

    inclusivecloggedcostheelold

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

    resetting progress for permanent boosts

    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
    焓
    0.46
    本身
    0.45
     갑
    0.44
     폐
    0.44
     ],"
    0.43
    ina
    0.42
    otro
    0.42
    ofer
    0.41
    atrol
    0.41
    irane
    0.41
    POSITIVE LOGITS
     blindly
    0.49
     propietarios
    0.48
    ᄈ
    0.48
     okresie
    0.48
     studied
    0.47
     unknowingly
    0.47
     costru
    0.46
     evaluated
    0.46
     stripped
    0.46
     життя
    0.46
    Activations Density 0.000%

    No Known Activations