© 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. 64430
    Prev
    Next
    INDEX
    Explanations

    profile and business details

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

    Introducing attributes or possessions

    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
    િલે
    0.45
    ატი
    0.44
    이드
    0.43
     faça
    0.42
     transformasi
    0.41
    Ⲡ
    0.41
    ضه
    0.40
    벵
    0.40
     Depos
    0.39
    ৰে
    0.39
    POSITIVE LOGITS
     Gainesville
    0.44
     Aleksandra
    0.42
     adress
    0.41
     装
    0.40
     学校
    0.40
     கல்லற
    0.40
    _
    0.39
    riele
    0.39
     Houston
    0.38
     dne
    0.38
    Activations Density 0.002%

    No Known Activations