© 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. 165654
    Prev
    Next
    INDEX
    Explanations

    past technological

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

    National Council

    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
     I
    0.51
     kare
    0.46
     ما
    0.45
     java
    0.44
     стру
    0.43
     rado
    0.43
     usare
    0.43
     रग
    0.42
     leben
    0.42
     wellness
    0.42
    POSITIVE LOGITS
    <unused90>
    0.51
     দ্রুত
    0.48
     அதிகரிக்கும்
    0.47
     তালিকায়
    0.45
     formie
    0.45
    ూ
    0.45
     இறுதியில்
    0.44
    ЕР
    0.44
     விரைவில்
    0.44
    वृद्धि
    0.44
    Activations Density 0.001%

    No Known Activations