© 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. 203135
    Prev
    Next
    INDEX
    Explanations

    additionally, even, or

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

    foreign and abstract concepts

    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
    プ
    0.49
     આપણે
    0.46
     हंसी
    0.45
    簽證
    0.45
    zechos
    0.44
    凖
    0.44
     संग्रहालय
    0.43
    museum
    0.43
    電源
    0.43
    生理
    0.43
    POSITIVE LOGITS
    잦
    0.46
    OGRAM
    0.46
     prad
    0.44
     distinguishable
    0.43
     blocking
    0.43
     стрельца
    0.43
     Wam
    0.43
     mittels
    0.42
     inverses
    0.42
     atleast
    0.42
    Activations Density 0.000%

    No Known Activations