© 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. 236656
    Prev
    Next
    INDEX
    Explanations

    appreciation and obtaining

    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
     線
    0.47
    فرض
    0.44
     gyak
    0.44
    WARF
    0.43
     گاه
    0.43
     kú
    0.43
    حدى
    0.42
    經常
    0.41
    學者
    0.41
     陳
    0.41
    POSITIVE LOGITS
    则是
    0.51
    为什么要
    0.49
    为什么
    0.47
     mentioning
    0.44
    员
    0.42
    龛
    0.42
     उसको
    0.41
     paiement
    0.41
    怎么
    0.41
    应该
    0.41
    Activations Density 0.002%

    No Known Activations