© 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. 3078
    Prev
    Next
    INDEX
    Explanations

    Donations and financial terms

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

    album quality

    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
     ఎమ్
    0.59
    ӓ
    0.49
     ফস
    0.47
     ক্যাম
    0.46
     नाइट्र
    0.45
    𝘺
    0.45
    comed
    0.44
    gráf
    0.43
     каме
    0.42
    𝘬
    0.42
    POSITIVE LOGITS
    Donate
    0.38
    Roman
    0.37
    Ethereum
    0.37
    ("
    0.35
    BTC
    0.35
    Remember
    0.35
    全身
    0.34
    ใจ
    0.34
    一个个
    0.34
    汪
    0.34
    Activations Density 0.000%

    No Known Activations