© 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. 161148
    Prev
    Next
    INDEX
    Explanations

    Non-English language names or technical terms

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

    POD Platforms and algorithms

    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
     altri
    0.52
    1
    0.49
     beach
    0.48
     ока
    0.47
    갯
    0.46
    beach
    0.46
    对
    0.46
    上海
    0.46
    2
    0.46
    journal
    0.45
    POSITIVE LOGITS
    akkhati
    0.49
     tasmim
    0.46
     Sinhalese
    0.46
    avasena
    0.45
    HasFieldError
    0.45
     armada
    0.45
    iagnosed
    0.44
    閇
    0.44
     ஆய
    0.44
    abhave
    0.44
    Activations Density 0.000%

    No Known Activations