© 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. 105192
    Prev
    Next
    INDEX
    Explanations

    foreign language or TikTok

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

    measurement, matters, cycle, options

    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
     limites
    0.59
     antigos
    0.51
     ideales
    0.50
     ennemis
    0.48
    황
    0.47
     généraux
    0.47
     zeuden
    0.46
    nuxt
    0.46
    在
    0.45
    ᒫ
    0.45
    POSITIVE LOGITS
    chord
    0.45
     వారి
    0.44
     परिस्थिति
    0.44
     TikTok
    0.44
     Tiktok
    0.43
    त
    0.42
     यज्ञ
    0.42
     оценки
    0.42
     සම්බන්ධ
    0.41
    ProductRunnable
    0.41
    Activations Density 0.000%

    No Known Activations