© 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. 97222
    Prev
    Next
    INDEX
    Explanations

    hierarchy or container

    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
     entsprechend
    0.45
    ของผู้
    0.40
     Vacc
    0.38
     स्टैट
    0.38
     دختر
    0.38
     zusätzliche
    0.37
    über
    0.37
     }^{\
    0.37
    ܪ
    0.37
    𝙧
    0.37
    POSITIVE LOGITS
     Fili
    0.41
    ലാണ്
    0.40
    ecs
    0.38
    kan
    0.38
     অধ্যাপ
    0.37
     रणनीति
    0.37
     xét
    0.37
     scheme
    0.36
    ipzig
    0.36
    lems
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.