© 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. 21318
    Prev
    Next
    INDEX
    Explanations

    afterwards or then

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

    relationship descriptors

    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
     уте
    0.47
     уту
    0.44
     kanske
    0.41
     etiam
    0.41
    кнове
    0.41
    뿐
    0.41
     말고
    0.40
    ジョ
    0.40
    разу
    0.40
    готовить
    0.39
    POSITIVE LOGITS
     Hygien
    0.48
     Reinforced
    0.47
     ત્યારબાદ
    0.44
     Afterwards
    0.44
     Clin
    0.43
     பின்னர்
    0.42
     klin
    0.42
     Separate
    0.42
     سپس
    0.42
     reinforced
    0.41
    Activations Density 0.004%

    No Known Activations