© 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. 117369
    Prev
    Next
    INDEX
    Explanations

    completion via

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

    safe/debris, complex, practical, positive qualifiers

    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
    嬅
    0.49
    isyon
    0.48
    <unused49>
    0.47
    ัตว์
    0.47
    ใ
    0.47
    <unused14>
    0.46
     natthi
    0.46
    atil
    0.45
     জিজ্ঞাস
    0.45
    eers
    0.44
    POSITIVE LOGITS
    PRE
    0.48
     山
    0.48
     BIG
    0.47
    BTW
    0.47
     definitivo
    0.46
     quinto
    0.46
     D
    0.45
    1
    0.45
    IO
    0.45
     translational
    0.45
    Activations Density 0.001%

    No Known Activations