© 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. 60594
    Prev
    Next
    INDEX
    Explanations

    showers or rain

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

    catfight invitation

    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
    同時に
    0.52
    ্যতা
    0.50
     affirme
    0.45
    Hv
    0.45
    ೊಂದಿಗೆ
    0.45
    okkaido
    0.45
     rescaling
    0.45
    എ
    0.44
     erstmals
    0.44
     เนาะ
    0.44
    POSITIVE LOGITS
     Call
    0.54
     Calculator
    0.45
     Plan
    0.45
     Calvin
    0.44
     Cast
    0.44
     콜
    0.44
     Gas
    0.43
     Brew
    0.43
     Smoking
    0.42
     Deacon
    0.42
    Activations Density 0.000%

    No Known Activations