© 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. 216700
    Prev
    Next
    INDEX
    Explanations

    reports, universe, temporal replication

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

    extremely difficult, highly unlikely

    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
     मिरर
    0.52
    тре
    0.51
     রাজশ
    0.51
     본격
    0.50
     ලැබ
    0.49
    КУ
    0.48
    सेवी
    0.48
    ḡ
    0.48
     이름
    0.47
     referentes
    0.47
    POSITIVE LOGITS
     infil
    0.46
    Conte
    0.45
    rog
    0.45
    orn
    0.43
     snd
    0.43
     incum
    0.43
     assol
    0.42
     rou
    0.42
    IER
    0.41
    SOLID
    0.41
    Activations Density 0.000%

    No Known Activations