© 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. 33475
    Prev
    Next
    INDEX
    Explanations

    concessive conjunctions such as although

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

    url paths and conditions

    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
     huh
    0.42
     theory
    0.40
     mats
    0.40
     sand
    0.40
     Hmm
    0.39
     Sandusky
    0.39
    ط
    0.38
     tuple
    0.38
    Txt
    0.37
     vapeur
    0.37
    POSITIVE LOGITS
    虽然
    0.44
    Although
    0.43
    雖
    0.43
    although
    0.41
    虽
    0.40
    雖然
    0.40
    อกจาก
    0.39
     арти
    0.39
     Иль
    0.38
    னோ
    0.38
    Activations Density 0.000%

    No Known Activations