© 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. 150282
    Prev
    Next
    INDEX
    Explanations

    cathode chamber

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

    nuanced perceptions

    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
     descub
    0.46
     discoveries
    0.44
     canoe
    0.43
     ترکیب
    0.43
    汤
    0.42
     أحد
    0.42
    šn
    0.42
     pari
    0.41
    ంత్ర
    0.40
    ḵ
    0.40
    POSITIVE LOGITS
    Align
    0.45
    enqueue
    0.44
    Quaternion
    0.44
    まれ
    0.44
    ंपरिक
    0.43
    didReceive
    0.43
    decrement
    0.43
    দর্শনে
    0.42
    ुए
    0.41
    निष्ठ
    0.41
    Activations Density 0.001%

    No Known Activations