© 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. 52450
    Prev
    Next
    INDEX
    Explanations

    potential harm or relationship issues

    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
    时间内
    0.43
    魅力
    0.42
    nextInt
    0.41
    toByteArray
    0.40
    事が
    0.40
     gust
    0.39
    u
    0.39
     vidéo
    0.39
    SUPER
    0.39
    żej
    0.39
    POSITIVE LOGITS
     архі
    0.54
     boucle
    0.52
     高級
    0.51
     alle
    0.50
     '')
    0.48
     บ
    0.47
     OCLC
    0.46
     দক্ষিণ
    0.46
    gebaut
    0.46
     দেখিলাম
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.