© 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. 86542
    Prev
    Next
    INDEX
    Explanations

    authentication services

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

    cost-effective simulation

    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
    로
    0.56
    '
    0.55
    ◍
    0.55
    ેલ
    0.51
    ின்
    0.51
    ’
    0.51
     ко
    0.50
    то
    0.50
    Frank
    0.49
     награ
    0.48
    POSITIVE LOGITS
     نفسك
    0.44
     INCREASE
    0.41
     aumentó
    0.40
     puedes
    0.40
    হইল
    0.39
    輿
    0.39
     শিক্ষার্থীরা
    0.39
     earthqu
    0.38
    िएंट
    0.38
     augmente
    0.38
    Activations Density 0.005%

    No Known Activations