© 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. 126209
    Prev
    Next
    INDEX
    Explanations

    scenery and costs

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

    isolating, halting, or subsequent actions

    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
    說
    0.43
    注目
    0.42
     stallion
    0.42
    束
    0.42
     Wrangler
    0.41
    ěl
    0.40
    Business
    0.40
    説
    0.40
     distillery
    0.39
    곶
    0.39
    POSITIVE LOGITS
     書い
    0.56
     Ты
    0.50
     propias
    0.50
     일부
    0.49
     मांसपेश
    0.49
    ifie
    0.47
     دیگری
    0.47
     บ้าง
    0.47
     写
    0.46
     τότε
    0.46
    Activations Density 0.001%

    No Known Activations